INDEX
Explanations
references to the Clinton family
mentions of the name "Clinton."
New Auto-Interp
Negative Logits
T
-0.75
F
-0.74
E
-0.74
regular
-0.74
AA
-0.73
L
-0.73
C
-0.72
M
-0.71
D
-0.71
Ah
-0.69
POSITIVE LOGITS
Clinton
3.00
Hillary
2.25
Sanders
2.07
Romney
1.90
Democrats
1.79
clinton
1.78
Bernie
1.63
Trump
1.62
INTON
1.59
Obama
1.57
Activations Density 0.018%