Go to NeurIPS 2025 Workshop WiML homepageDistributed Specialization: How Transformers Process Rare Tokens Through Parameter Differentiation
Keywords: large language models, mechanistic interpretability
Submission Number: 154
Loading
OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2026 OpenReview