INDEX
Explanations
mentions of the name "Hillary Clinton"
mentions of Hillary Clinton
New Auto-Interp
Negative Logits
iple
-0.78
otal
-0.73
ENSE
-0.72
ribune
-0.72
âķIJ
-0.72
pec
-0.71
outer
-0.67
venants
-0.67
inctions
-0.67
peed
-0.67
POSITIVE LOGITS
Rodham
1.70
Clinton
1.58
Clinton
1.27
clinton
1.11
Clintons
1.10
INTON
1.09
Diane
1.03
Hillary
0.99
DeVos
0.95
Hillary
0.84
Activations Density 0.021%