INDEX
Explanations
references to Bill and Hillary Clinton in various contexts
New Auto-Interp
Negative Logits
MeasureSpec
-0.58
rospy
-0.53
yarar
-0.49
ItemBackground
-0.48
袱
-0.48
نب
-0.48
Telefax
-0.48
sense
-0.47
sea
-0.46
préfé
-0.45
POSITIVE LOGITS
Clinton
1.19
Clinton
1.19
CLIN
0.70
CLIN
0.61
Hillary
0.57
inton
0.54
Clint
0.54
Clint
0.53
Hillary
0.51
Clin
0.51
Activations Density 0.006%