INDEX
Explanations
references to Internet Explorer
New Auto-Interp
Negative Logits
ifar
-0.17
bjerg
-0.16
zÃŃ
-0.15
διά
-0.15
ecies
-0.15
idget
-0.14
akeup
-0.14
andest
-0.14
uslim
-0.14
edith
-0.14
POSITIVE LOGITS
IE
0.28
IE
0.27
lt
0.21
shiv
0.20
ie
0.20
=edge
0.19
Modern
0.19
ie
0.19
lte
0.19
shim
0.18
Activations Density 0.087%