INDEX
Explanations
mentions of individuals named Barbara
New Auto-Interp
Negative Logits
nia
-0.15
URAL
-0.15
ÑĢÑĥд
-0.14
arı
-0.14
tings
-0.14
lle
-0.14
ÃŃrk
-0.13
à¹ĥส
-0.13
rine
-0.13
aukee
-0.13
POSITIVE LOGITS
Ann
0.19
bara
0.18
Box
0.17
rient
0.16
Bush
0.16
Walters
0.15
.gdx
0.15
Jean
0.15
fter
0.15
Kings
0.15
Activations Density 0.006%