INDEX
Explanations
references to licenses and places
New Auto-Interp
Negative Logits
azzo
-0.17
ario
-0.15
rish
-0.14
osti
-0.14
olla
-0.14
plá
-0.14
lady
-0.14
θι
-0.14
924
-0.13
996
-0.13
POSITIVE LOGITS
amar
0.15
anj
0.15
Äįek
0.15
scar
0.15
truncate
0.14
Apex
0.14
lore
0.14
Nug
0.14
ãĤģ
0.14
oram
0.14
Activations Density 0.003%