INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
as
1.23
;
1.20
at
1.14
س
1.12
ن
1.01
strane
0.95
}
0.95
to
0.93
*}
0.90
:”
0.89
POSITIVE LOGITS
خدام
1.11
ع
1.10
ﺭ
1.10
보는
1.08
ایی
1.07
ри
1.05
ın
1.02
'
1.01
ла
1.00
gp
1.00
Activations Density 0.000%