Goodfire AI Research: Efficiently Locating 'Forking Tokens' in LLMs

VoidAsuka · x · 2026-08-27

Goodfire AI has released new research on a technique that locates 'forking tokens' leading to different model trajectories 100x more efficiently than current methods. Aiming to help truly understand and debug models, the research treats LLMs like Schrödinger's cat, revealing internal behaviors by identifying key decision points.

Original post →

More from Models

Models channel →