In Machina N400: Pinpointing Where a Causal Language Model Detects Semantic Violations

Documenti analoghi

• Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering
  di: Zacharopoulos, Christos-Nikolaos, et al.
  Pubblicazione: (2025)
• Multilingual corpora for the study of new concepts in the social sciences and humanities:
  di: Kyriakoglou, Revekka, et al.
  Pubblicazione: (2025)
• Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
  di: Deng, Ruixuan, et al.
  Pubblicazione: (2025)
• Where does output diversity collapse in post-training?
  di: Karouzos, Constantinos, et al.
  Pubblicazione: (2026)
• Where does In-context Translation Happen in Large Language Models
  di: Sia, Suzanna, et al.
  Pubblicazione: (2024)