OpenInterpretability
Open-source toolkit to audit what your LLM knows
OpenInterpretability이란?
The first mech interp toolkit that runs inside Claude Code, Cursor, and Cline via MCP. Production probes (FabricationGuard, agent-probe-guard) catch hallucinations + agent failures. ProbeBench leaderboard, SAE training from 30-min free Colab to paper-grade. Apache-2.0.
스크린샷
?
아직 댓글이 없어요. 가장 먼저 남겨보세요!
OpenInterpretability에 대한 X의 실제 대화
X에 게시