INDEX
Explanations
occurrences of the term "Jew" in various contexts
New Auto-Interp
Negative Logits
bic
-0.16
ustin
-0.15
éķ
-0.15
quirer
-0.14
afx
-0.14
AuthService
-0.14
PÅĻed
-0.14
.protobuf
-0.14
ushman
-0.14
aler
-0.14
POSITIVE LOGITS
sm
0.19
iat
0.17
ifo
0.17
eren
0.16
eless
0.16
SM
0.16
783
0.15
.construct
0.15
ettle
0.15
808
0.14
Activations Density 0.003%