INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
孭
2.21
ungannya
2.19
爌
2.14
烩
2.05
сле
2.03
olidated
2.03
^{*}=\2.02
yake
2.02
|=\
2.00
پ
2.00
POSITIVE LOGITS
7
1.88
6
1.70
8
1.67
5
1.58
0
1.56
4
1.50
3
1.38
9
1.34
2
1.16
ASK
0.84
Activations Density 1.223%