INDEX
Explanations
mentions of controversy or criticism involving public figures
New Auto-Interp
Negative Logits
rompecabezas
-0.38
templado
-0.33
usually
-0.33
grø
-0.30
always
-0.30
conferir
-0.30
semper
-0.29
ITZER
-0.28
limpio
-0.28
kesin
-0.28
POSITIVE LOGITS
findpost
0.82
allegedly
0.81
controversial
0.75
controversy
0.75
alleged
0.74
alleg
0.74
polémica
0.73
controversi
0.73
criticised
0.71
Controversy
0.70
Activations Density 0.535%