INDEX
Negative Logits
しの
1.68
saver
1.66
her
1.65
evidence
1.63
她在
1.61
relief
1.55
佢
1.53
ients
1.52
herself
1.50
tutorials
1.50
POSITIVE LOGITS
6
2.62
7
2.62
9
2.61
8
2.59
2
2.54
5
2.34
4
2.29
3
2.21
req
1.97
1
1.90
Activations Density 0.089%
しの
saver
her
evidence
她在
relief
佢
ients
herself
tutorials
6
7
9
8
2
5
4
3
req
1