INDEX
Explanations
references to the United Nations Security Council and its activities
New Auto-Interp
Negative Logits
´Ģ
-0.18
kinson
-0.16
odzi
-0.15
oby
-0.15
fal
-0.15
usra
-0.15
ÃŃky
-0.14
adb
-0.14
लब
-0.14
opp
-0.14
POSITIVE LOGITS
alie
0.16
ebi
0.15
yonel
0.15
cene
0.15
483
0.14
Underground
0.14
gli
0.14
ekl
0.14
ober
0.14
abuse
0.14
Activations Density 0.009%