INDEX
Explanations
keywords related to ongoing debates or controversies
occurrences of the word "debate" and related discussions
New Auto-Interp
Negative Logits
amina
-0.69
uras
-0.68
iaries
-0.66
urances
-0.65
hetical
-0.65
liner
-0.64
urance
-0.63
oiler
-0.62
ogly
-0.62
ractions
-0.61
POSITIVE LOGITS
naire
0.82
raging
0.81
puff
0.79
raged
0.78
debate
0.77
moderators
0.73
halla
0.73
discussion
0.70
dayName
0.70
debated
0.69
Activations Density 0.027%