INDEX
Negative Logits
screw
-0.08
pav
-0.08
Learned
-0.07
vex
-0.07
jav
-0.07
ernet
-0.07
Joke
-0.07
slave
-0.07
Born
-0.07
પડ
-0.07
POSITIVE LOGITS
sáng
0.10
brightly
0.09
-lit
0.08
KIT
0.08
-cut
0.08
mạnh
0.08
κ
0.08
itoare
0.08
ട്ട
0.08
cảm
0.07
Activations Density 0.007%