INDEX
Explanations
expressions of past and present actions or states involving people and children
New Auto-Interp
Negative Logits
indle
-0.16
ificados
-0.15
WXYZ
-0.15
овиÑĩ
-0.15
pmat
-0.14
Copyright
-0.14
اÙĦع
-0.14
´Ī
-0.14
verture
-0.14
uguay
-0.14
POSITIVE LOGITS
ka
0.15
ert
0.14
aster
0.14
ERC
0.14
eren
0.14
731
0.14
Gew
0.13
mez
0.13
allo
0.13
_RESOLUTION
0.13
Activations Density 0.570%