INDEX
Explanations
references to voting, public decisions, and related political themes
New Auto-Interp
Negative Logits
hers
-0.16
ioc
-0.15
zas
-0.15
osaur
-0.15
asley
-0.14
lero
-0.14
ngth
-0.14
IOC
-0.14
алог
-0.14
ارÙĩ
-0.13
POSITIVE LOGITS
clin
0.15
çīĩ
0.15
.Relative
0.14
ãĤ¢ãĥ³
0.14
enced
0.14
761
0.13
oppos
0.13
mont
0.13
WindowSize
0.13
747
0.13
Activations Density 0.403%