INDEX
Explanations
references to ancient traditions and pagan celebrations
New Auto-Interp
Negative Logits
+#+#
-0.51
Uri
-0.46
Protestantism
-0.45
Vidite
-0.45
Shakspeare
-0.44
ukone
-0.44
queryInterface
-0.44
ImageContext
-0.42
Suf
-0.41
Roskov
-0.41
POSITIVE LOGITS
griego
0.59
picioare
0.59
Infór
0.54
desnuda
0.53
desecha
0.52
anún
0.52
cenar
0.52
griega
0.52
grecque
0.51
sapere
0.50
Activations Density 0.484%