INDEX
Explanations
proper nouns and specific names
New Auto-Interp
Negative Logits
transfieras
-0.48
Houſe
-0.44
reaſon
-0.44
Eſ
-0.42
Conſ
-0.41
ویکیپدی
-0.41
Chriſt
-0.40
Reſ
-0.40
ſtre
-0.39
ftagPool
-0.39
POSITIVE LOGITS
inato
0.43
HasFactory
0.42
rsiniz
0.41
darbu
0.40
descobri
0.40
RTEX
0.39
publicados
0.39
publicado
0.39
DISE
0.39
GIH
0.38
Activations Density 3.548%