INDEX
Negative Logits
ST
-0.68
CD
-0.66
C
-0.66
CC
-0.65
MR
-0.65
K
-0.64
R
-0.64
L
-0.64
SE
-0.63
SG
-0.63
POSITIVE LOGITS
e
0.50
a
0.46
ez
0.43
s
0.40
ed
0.39
i
0.38
ep
0.36
en
0.36
em
0.36
eb
0.36
Activations Density 0.179%
ST
CD
C
CC
MR
K
R
L
SE
SG
e
a
ez
s
ed
i
ep
en
em
eb