INDEX
Explanations
references to political accountability or consequences related to border and international issues
New Auto-Interp
Negative Logits
aland
-0.16
OVID
-0.14
owi
-0.14
@_
-0.14
jÃŃt
-0.13
COVID
-0.13
ει
-0.13
.appspot
-0.13
aspers
-0.13
acos
-0.13
POSITIVE LOGITS
ictim
0.15
FML
0.14
chine
0.14
ipt
0.14
EAR
0.13
media
0.13
dou
0.13
otti
0.13
620
0.13
online
0.13
Activations Density 0.099%