INDEX
Explanations
mentions of a specific individual, Betsy DeVos
New Auto-Interp
Negative Logits
orden
-0.17
orest
-0.16
hift
-0.16
alat
-0.15
inely
-0.15
Brit
-0.14
perienced
-0.14
lease
-0.14
견
-0.14
Gig
-0.13
POSITIVE LOGITS
ENTIC
0.16
еб
0.14
Ỽ
0.14
ennai
0.14
impl
0.14
yo
0.14
otle
0.14
Alternate
0.14
Tie
0.14
Schwarz
0.13
Activations Density 0.004%