INDEX
Explanations
geographical references and locations associated with burial sites
New Auto-Interp
Negative Logits
STRUCTION
-0.66
ferien
-0.60
omyia
-0.55
]--;
-0.54
gans
-0.52
ratie
-0.51
rute
-0.50
قایناقلار
-0.50
STRUCTIONS
-0.49
sé
-0.49
POSITIVE LOGITS
'\\;'
0.82
communiquez
0.72
PLWABN
0.63
الحره
0.63
0.59
ništvo
0.58
BufferException
0.57
Италијани
0.57
niająca
0.57
✭✭
0.56
Activations Density 0.002%