OpenInterpretability
Open-source toolkit to audit what your LLM knows
¿Qué es OpenInterpretability?
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.
Capturas de pantalla
?
Aún no hay comentarios. ¡Sé el primero!
Conversaciones reales sobre OpenInterpretability en X
Publicar en X