Activation probes
Named by 2 kept items in this workspace.
Search every workspace for Activation probes. It matches the name as written, so it can find other things that share it.
The items that name it 2
Lightweight classifiers that look for concerning patterns in a model's internal activations and pass flagged cases to the next layer.
Small transformers that read the model's internal neural signals to spot when it is activating knowledge about cyberattacks or biological threats
All technologies in this workspace.