INDEX
Negative Logits
imum
-0.08
uco
-0.07
LX
-0.07
(Index
-0.07
Spot
-0.07
ります
-0.07
nogi
-0.07
MAP
-0.07
ponents
-0.07
-0.07
POSITIVE LOGITS
excessive
0.12
reinvent
0.11
overly
0.11
undue
0.10
copyrighted
0.10
unnecessary
0.09
overcrow
0.09
exhaustive
0.09
obsessive
0.09
proprietary
0.08
Activations Density 0.035%