INDEX
Explanations
discussions about political support and legislative actions related to conservatism
New Auto-Interp
Negative Logits
oser
-0.18
allenge
-0.16
sko
-0.15
лиж
-0.15
izons
-0.14
agina
-0.14
SPELL
-0.14
alten
-0.14
iffies
-0.14
ailable
-0.13
POSITIVE LOGITS
talk
0.35
-talk
0.28
talk
0.27
Talk
0.26
Talk
0.26
claims
0.25
talks
0.23
Claims
0.23
claimed
0.22
talking
0.22
Activations Density 0.499%