INDEX
Explanations
concepts related to racial equity and systemic racism
New Auto-Interp
Negative Logits
tam
-0.16
Affero
-0.14
motor
-0.14
Bilg
-0.14
à¥Īय
-0.14
apost
-0.13
erse
-0.13
æĻ¨
-0.13
ÑĬ
-0.13
.jetbrains
-0.13
POSITIVE LOGITS
whites
0.17
systematic
0.15
racism
0.15
system
0.15
perpet
0.15
rema
0.15
segregation
0.15
systems
0.15
subtle
0.15
System
0.14
Activations Density 0.185%