-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 139 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 119 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 294 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 126
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
View all activity
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 283 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 232 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 230 -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 199
-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 139 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 119 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 294 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 126
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 283 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 232 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 230 -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 199