INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
۔
0.98
().
0.97
**.
0.91
。
0.90
։
0.83
².
0.82
ومن
0.82
وم
0.81
де
0.80
which
0.79
POSITIVE LOGITS
hasn
1.29
isn
1.24
wasn
1.21
doesn
1.19
is
1.15
has
1.11
may
1.11
weren
1.09
didn
1.09
りは
1.08
Activations Density 1.378%