INDEX
Explanations
proper names or entities containing the word "Milo"
mentions of a specific individual, Milo Yiannopoulos
New Auto-Interp
Negative Logits
marked
-0.81
mark
-0.81
marks
-0.80
pring
-0.79
master
-0.78
Cherokee
-0.76
lain
-0.69
mary
-0.68
session
-0.68
chool
-0.66
POSITIVE LOGITS
fty
1.07
cean
1.06
Yiannopoulos
0.99
Å¡
0.99
leans
0.87
zek
0.86
Princ
0.84
zzi
0.83
qu
0.80
henko
0.80
Activations Density 0.027%