INDEX
Negative Logits
lte
-0.15
amburger
-0.15
_ASSUME
-0.15
UTERS
-0.14
جر
-0.14
ponge
-0.14
FN
-0.14
еком
-0.14
istring
-0.14
estre
-0.14
POSITIVE LOGITS
IntelliJ
0.17
ung
0.16
uk
0.15
appy
0.15
hon
0.15
ODE
0.15
up
0.15
ged
0.15
Project
0.14
дам
0.14
Activations Density 0.013%