INDEX
Explanations
words related to riots
occurrences of the word "riot" and its variations
New Auto-Interp
Negative Logits
DonaldTrump
-0.76
hran
-0.74
bourg
-0.72
iban
-0.70
ournal
-0.70
omething
-0.70
ULTS
-0.69
hered
-0.69
avez
-0.66
therap
-0.65
POSITIVE LOGITS
ous
1.01
naire
0.92
ously
0.88
ers
0.88
ing
0.84
rained
0.83
auld
0.82
eering
0.79
aries
0.78
riot
0.77
Activations Density 0.029%