INDEX
Negative Logits
Communication
-0.08
See
-0.08
SEE
-0.08
transferência
-0.08
fer
-0.08
93
-0.08
schrijft
-0.08
kommunik
-0.07
transferring
-0.07
pissed
-0.07
POSITIVE LOGITS
info
0.08
நல்ல
0.08
tc
0.08
cb
0.07
dc
0.07
dc
0.07
0.07
unsafe
0.07
tc
0.07
.cb
0.07
Activations Density 0.006%