INDEX
Explanations
not started or not applicable
New Auto-Interp
Negative Logits
Tomb
0.42
Tune
0.41
Tompkins
0.38
butch
0.37
Homeland
0.37
Побе
0.37
όχι
0.36
CID
0.36
iddi
0.36
Religion
0.35
POSITIVE LOGITS
permettre
0.44
以上
0.42
offrire
0.41
permitting
0.40
objectionable
0.40
pozwoli
0.39
belong
0.39
дать
0.39
EDEN
0.38
slept
0.37
Activations Density 0.000%