INDEX
Explanations
phrases related to political controversies and statements
New Auto-Interp
Negative Logits
097
-0.16
hte
-0.15
gett
-0.14
Ì£
-0.14
%p
-0.14
()↵↵
-0.14
idenav
-0.13
pace
-0.13
geb
-0.13
BÃł
-0.13
POSITIVE LOGITS
SEE
0.15
ero
0.14
vocal
0.14
IMAGE
0.14
Related
0.14
tslint
0.13
via
0.13
omo
0.13
ideo
0.13
utsche
0.13
Activations Density 0.133%