INDEX
Explanations
public affairs and concepts
New Auto-Interp
Negative Logits
当時
0.39
когда
0.36
damals
0.35
每個
0.35
悰
0.35
مت
0.34
וה
0.34
،
0.34
vì
0.33
والأ
0.33
POSITIVE LOGITS
सार्वजनिक
0.39
犯罪
0.36
violación
0.35
prosecutor
0.35
can
0.35
spokesman
0.34
provocative
0.34
<unused1018>
0.34
portavoz
0.34
will
0.34
Activations Density 0.218%