INDEX
Explanations
references to electoral politics and candidates in the context of elections
New Auto-Interp
Head Attr Weights
0:0.02
1:0.04
2:0.10
3:0.07
4:0.04
5:0.06
6:0.06
7:0.12
8:0.17
9:0.11
10:0.08
11:0.08
Negative Logits
urb
-1.15
orb
-1.13
ophys
-1.05
cavern
-1.01
oop
-1.00
Realms
-1.00
etheless
-0.99
circle
-0.98
merce
-0.97
Quarterly
-0.97
POSITIVE LOGITS
aeda
1.17
outwe
1.13
actionGroup
1.11
=>
1.08
�
1.07
utsch
1.05
裏
1.03
nesty
1.03
instead
1.03
reasons
1.03
Activations Density 0.023%