-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 610 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 148 -
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 582k • 220 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 570
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
View all activity
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 610 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 148 -
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 582k • 220 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 570
models 0
None public yet
datasets 11
PersonaBias/Reverse-alpha-beta-no-outside
Viewer • Updated • 5.04M • 75
PersonaBias/Reverse-alpha-suppression-task-boost
Viewer • Updated • 5.39M • 548
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 610
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 148
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 582k • 220
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 570
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 369
PersonaBias/Reverse-baseline-bias-unbias
Viewer • Updated • 5.95M • 601
PersonaBias/counterfactuals
Viewer • Updated • 505k • 782
PersonaBias/bias_evaluation_sets
Viewer • Updated • 281k • 373