INDEX
Explanations
references to monasticism or associated concepts
New Auto-Interp
Negative Logits
elles
-0.18
ellas
-0.17
iloc
-0.15
ENDED
-0.15
GRE
-0.15
ÑĪов
-0.15
itched
-0.14
iles
-0.14
wrapped
-0.14
YE
-0.14
POSITIVE LOGITS
IVA
0.18
iva
0.16
foreign
0.15
ivas
0.15
oyo
0.15
Orth
0.15
pawn
0.14
Lng
0.14
Poster
0.14
magn
0.14
Activations Density 0.022%