{"total":23,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2206.15465","title":"Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values","created":"2022-06-30","cited_by_count":25,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2112.03245","title":"GAM Changer: Editing Generalized Additive Models with Interactive Visualization","created":"2021-12-06","cited_by_count":18,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2311.15983","title":"SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2103.00573","title":"RuSentEval: Linguistic Source, Encoder Force!","created":"2021-02-28","cited_by_count":4,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2504.13856","title":"Towards Balancing Preference and Performance through Adaptive Personalized Explainability","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2210.09990","title":"Post-hoc analysis of Arabic transformer models","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2309.12263","title":"On the Relationship between Skill Neurons and Robustness in Prompt Tuning","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2510.16851","title":"Neuronal Group Communication for Efficient Neural representation","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2201.07434","title":"Interpreting Arabic Transformer Models","created":"2022-01-19","cited_by_count":0,"area":null},{"id":"2604.11802","title":"Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?","created":"2026-04-13","cited_by_count":0,"area":null}],"next_cursor":null}