INDEX
Explanations
words related to possession and belonging
New Auto-Interp
Negative Logits
ÃŃc
-0.17
ther
-0.15
ipes
-0.15
.
-0.15
tae
-0.15
.InnerException
-0.14
ishops
-0.14
beros
-0.14
á»Ńi
-0.14
262
-0.14
POSITIVE LOGITS
ient
0.47
iens
0.35
ienne
0.32
enu
0.31
IENT
0.30
enez
0.30
ien
0.27
i
0.26
ENU
0.26
ients
0.23
Activations Density 0.008%