INDEX
Explanations
city followed by name or descriptor
New Auto-Interp
Negative Logits
ين
1.54
ל
1.40
ل
1.37
ك
1.19
ва
1.17
л
1.16
ת
1.16
رك
1.13
ס
1.09
as
1.08
POSITIVE LOGITS
1
1.25
t
1.20
I
1.09
ong
1.08
I
0.99
_
0.98
あ
0.95
h
0.93
City
0.93
f
0.93
Activations Density 0.022%