INDEX
Explanations
words related to debate and discussion
mentions of ongoing discussions or controversies
New Auto-Interp
Negative Logits
iaries
-0.77
fits
-0.72
undai
-0.70
uras
-0.68
oho
-0.66
photos
-0.65
AMI
-0.65
imus
-0.64
iak
-0.64
amina
-0.62
POSITIVE LOGITS
raging
1.03
raged
0.96
concerning
0.85
regarding
0.83
moderators
0.82
iveness
0.82
halla
0.80
debates
0.80
debate
0.79
naire
0.78
Activations Density 0.055%