Mechanistic interpretability: opening the black box to see how neural networks actually think
Neural Notions dives into Mechanistic interpretability: opening the black box to see how neural networks actually think.
0:00
26:58
Show notes
- Overview: Neural Notions dives into Mechanistic interpretability: opening the black box to see how neural networks actually think.
- Tags: artificial intelligence, AI agents
Links and references
- artificial intelligence
- AI agents
Episode Outline
Timestamped topic guide generated from the episode audio for quick scanning.
Loading transcript... [00:00] Neural Notions dives into Mechanistic interpretability: opening the black box to see how neural networks actually think.