INDEX
Negative Logits
Vice
-0.08
Vice
-0.08
Hi
-0.07
ursion
-0.07
@\
-0.07
-awareness
-0.07
halv
-0.07
posals
-0.07
جهت
-0.07
(>
-0.07
POSITIVE LOGITS
-linear
0.15
linear
0.14
_linear
0.13
linear
0.12
.linear
0.11
Linear
0.11
Linear
0.11
лин
0.10
_LINEAR
0.10
liner
0.09
Activations Density 0.027%