INDEX
Explanations
mentions of the name "Hillary Rodham Clinton"
references to Hillary Rodham Clinton
New Auto-Interp
Negative Logits
Common
-0.82
tered
-0.72
Myth
-0.65
orne
-0.63
predictive
-0.62
Myth
-0.61
Californ
-0.60
Finnish
-0.58
occurrence
-0.58
ORN
-0.57
POSITIVE LOGITS
Rodham
1.34
clinton
1.11
Clinton
1.07
Clintons
0.90
INTON
0.89
Clinton
0.89
assetsadobe
0.88
ette
0.77
velt
0.77
rolet
0.76
Activations Density 0.010%