INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
یم
1.63
ות
1.15
یس
1.13
em
1.13
!
1.13
on
1.12
การ
1.07
it
1.06
?
1.05
ം
1.05
POSITIVE LOGITS
kenalkan
1.20
were
1.16
x
1.06
p
0.98
h
0.96
al
0.95
pertinente
0.91
và
0.91
이랑
0.91
在這個
0.89
Activations Density 0.000%