INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
ا
3.64
u
2.45
ان
2.39
ı
2.27
ை
2.16
่
2.16
на
2.13
0
2.09
ıya
1.94
f
1.88
POSITIVE LOGITS
fouling
2.06
ﺭ
1.93
challengers
1.90
argu
1.87
heaped
1.86
remedied
1.85
femora
1.85
ਬਰ
1.84
്യം
1.83
thisComponent
1.83
Activations Density 0.002%