INDEX
Explanations
names or titles related to politicians
references to political figures and their titles
New Auto-Interp
Negative Logits
sole
-0.77
hare
-0.76
rums
-0.75
crew
-0.74
queen
-0.73
foss
-0.73
obyl
-0.73
perm
-0.73
eat
-0.73
erie
-0.72
POSITIVE LOGITS
Tut
0.88
Stim
0.88
Candidate
0.88
Secretary
0.87
George
0.86
Barack
0.86
Leader
0.86
Lyndon
0.86
Abraham
0.86
Day
0.85
Activations Density 0.110%