INDEX
Negative Logits
این
-0.08
누구
-0.08
understandable
-0.08
oxidation
-0.08
sle
-0.08
'ac
-0.07
naho
-0.07
arrogance
-0.07
inte
-0.07
Scope
-0.07
POSITIVE LOGITS
ratio
0.10
Ratio
0.09
_ratio
0.08
徒
0.08
ratios
0.08
Ratio
0.08
_RATIO
0.08
olden
0.08
ratio
0.08
=my
0.07
Activations Density 0.022%