INDEX
Negative Logits
502
-0.08
533
-0.08
erosion
-0.08
ISC
-0.07
eros
-0.07
forth
-0.07
pheric
-0.07
inem
-0.07
etsk
-0.07
lord
-0.07
POSITIVE LOGITS
grabs
0.09
shining
0.08
joe
0.08
rolle
0.08
thi
0.08
�
0.08
(sh
0.08
grabbed
0.08
Mare
0.08
grabbing
0.07
Activations Density 0.001%