INDEX
Negative Logits
review
-1.47
review
-1.33
Review
-1.30
REVIEW
-1.28
Review
-1.27
reviewed
-1.17
REVIEW
-1.17
reviewing
-1.16
للاسماء
-1.11
myſelf
-1.07
POSITIVE LOGITS
-
0.75
0.72
<eos>
0.71
,
0.69
(
0.68
-
0.66
for
0.66
:
0.65
↵
0.63
.
0.63
Activations Density 1.124%