{"total":11,"rows":[{"id":"2506.20790","title":"Stochastic Parameter Decomposition","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2507.22216","title":"Representation biases: will we achieve complete understanding by analyzing representations?","created":"2025-07-29","cited_by_count":6,"area":null},{"id":"2410.00340","title":"Sparse Attention Decomposition Applied to Circuit Tracing","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2410.01334","title":"Skill Path: Unveiling Language Skills from Circuit Graphs","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2605.23039","title":"Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2606.16407","title":"A Mechanistic Understanding of Pronoun Fidelity in LLMs","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.20995","title":"Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}