INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
fr
0.64
이번
0.59
av
0.54
u
0.52
у
0.51
ful
0.51
ub
0.51
le
0.50
check
0.50
it
0.49
POSITIVE LOGITS
onwards
1.82
onward
1.45
silam
1.38
میل
1.24
ish
1.17
′,
1.10
以降
1.07
ISH
1.03
″
1.03
թվական
1.02
Activations Density 0.878%