INDEX
Explanations
mentions of political affiliations or ideologies, particularly referencing the right and left spectrum
New Auto-Interp
Negative Logits
ase
-0.16
Lag
-0.15
idi
-0.15
Gover
-0.14
illac
-0.14
ulk
-0.14
wise
-0.14
rr
-0.14
Interface
-0.14
Regions
-0.14
POSITIVE LOGITS
actionTypes
0.17
ushima
0.16
braco
0.15
Hudson
0.15
ento
0.14
utsch
0.14
éĻ
0.14
.mc
0.14
obao
0.14
aticon
0.14
Activations Density 0.059%