INDEX
Explanations
phrases related to social and political issues, particularly regarding human rights and freedom of expression
New Auto-Interp
Negative Logits
tribute
-0.14
jedn
-0.14
unami
-0.13
avras
-0.13
ibu
-0.13
731
-0.13
inem
-0.13
piece
-0.13
isci
-0.13
zos
-0.13
POSITIVE LOGITS
Ðĭ
0.14
525
0.14
AutoSize
0.14
545
0.13
stabil
0.13
oyal
0.13
ÏĦÏį
0.13
narr
0.12
è¼Ķ
0.12
LLU
0.12
Activations Density 0.224%