lasrprobegen/uncertainty-activations
Viewer
•
Updated
•
20k
•
38
LASR Probe Gen
Team
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
0
None public yet
datasets
12
lasrprobegen/bias-activations
Viewer
•
Updated
•
96.8k
•
397
lasrprobegen/authority-activations
Viewer
•
Updated
•
120k
•
565
lasrprobegen/sycophancy-activations
Viewer
•
Updated
•
143k
•
1.61k
lasrprobegen/refusal-activations
Viewer
•
Updated
•
10.2k
•
2.15k
•
1
lasrprobegen/science-activations
Preview
•
Updated
•
775
lasrprobegen/metaphors-activations
Preview
•
Updated
•
1.08k
lasrprobegen/lists-activations
Preview
•
Updated
•
920
lasrprobegen/deception-activations
Viewer
•
Updated
•
14k
•
690
•
1
lasrprobegen/sandbagging-activations
Preview
•
Updated
•
450