INDEX
Explanations
references to communism and socialist ideologies
New Auto-Interp
Negative Logits
tvb
-0.17
conserv
-0.15
Independ
-0.15
оналÑĮ
-0.14
Conserv
-0.14
sey
-0.14
hec
-0.14
Independence
-0.14
.validators
-0.14
inue
-0.14
POSITIVE LOGITS
-leaning
0.16
Workers
0.15
phia
0.15
uche
0.15
ische
0.15
workers
0.14
/left
0.14
isoft
0.14
plete
0.14
Worker
0.14
Activations Density 0.043%