-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 68 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 63 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 56 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 58
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 1.09k -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 629 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 1.05k -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 675
-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 68 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 63 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 56 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 58
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 1.09k -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 629 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 1.05k -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 675