conftrace_

internal mechanism

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

recurrent mechanism (1) activation mapping (1) causal evidence (1) transformer mechanistic analysis (1) symbolic multi-step reasoning (1) interpretable mechanism (1) depth-bounded recurrent mechanism (1) activation analysis (1) mechanistic analysis (1) neural network (1)

Papers

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms EMNLP 2025 Neurons to Words: A Novel Method for Automated Neural Network Interpretability and Alignment AAAI 2025 A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task ACL 2024