# The production of meaning in the processing of natural language

arXiv: https://arxiv.org/abs/2603.20381 · HTML: https://mlsanity.com/paper/2603.20381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge and representations inside LLMs, one of 13 directions in Mechanistic interpretability.
- Builds on 23 of its 72 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 23 of 23)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [The Quantization Model of Neural Scaling](https://mlsanity.com/paper/2303.13506/) (2023)
- [Locally Typical Sampling](https://mlsanity.com/paper/2202.00666/) (2022)
- [Understanding Emergent Abilities of Language Models from the Loss Perspective](https://mlsanity.com/paper/2403.15796/) (2024)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach](https://mlsanity.com/paper/2002.01092/) (2020)
- [Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching](https://mlsanity.com/paper/2311.17030/) (2023)
- [Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems](https://mlsanity.com/paper/2204.07666/) (2022)
- [Exploring the Impact of Temperature on Large Language Models:Hot or Cold?](https://mlsanity.com/paper/2506.07295/) (2025)
- [On the Efficacy of Sampling Adapters](https://mlsanity.com/paper/2307.03749/) (2023)
- [Spin and Wind Directions II: A Bell State Quantum Model](https://mlsanity.com/paper/1706.01188/) (2017)
- [A quantum semantic framework for natural language processing](https://mlsanity.com/paper/2506.10077/) (2025)
- [Spin and Wind Directions I: Identifying Entanglement in Nature and Cognition](https://mlsanity.com/paper/1508.00434/) (2015)
- [Quantum-Like Contextuality in Large Language Models](https://mlsanity.com/paper/2412.16806/) (2024)

## Built on by (most cited first, 1 of 1)

- [Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space](https://mlsanity.com/paper/2604.05030/) (2026)

## Abstract (arXiv)

Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions. If meaning is constituted rather than retrieved, then the search for context-independent features or circuits in the pursuit of mechanistic interpretability may be fundamentally limited. Experiments in cognitive science and social psychology have demonstrated that human semantic processing exhibits contextuality more consistent with quantum logical mechanisms than classical Boolean theories, and recent works have found similar results in large language models---in particular, clear violations of the Bell inequality in experiments of contextuality during interpretation of ambiguous expressions. In this work, we explore the CHSH |S| parameter---the metric associated with the inequality---across the inference parameter space of models spanning four orders of magnitude in scale and cross-reference our findings with MMLU, hallucination rate, and nonsense detection benchmarks. We find that the interquartile range of the |S| distribution is completely orthogonal to all external benchmarks, while overall violation rate shows weak anticorrelation with all three benchmarks. We investigate how |S| varies with sampling parameters and word order, and discuss the information-theoretic constraints that genuine contextuality imposes on prompt injection defenses and its human analogue, whereby careful construction and maintenance of social contextuality can be carried out at scale, shaping the space of possible interpretations before any particular one is reached. We consider the implications for mechanistic interpretability and how genuine contextuality sets an information-theoretic bound on the decomposability of semantic processing.