INDEX
Explanations
phrases related to legal rights and responsibilities
New Auto-Interp
Negative Logits
elen
-0.16
it
-0.16
layer
-0.15
udi
-0.15
Layer
-0.15
este
-0.14
av
-0.14
ôt
-0.14
lat
-0.14
abol
-0.14
POSITIVE LOGITS
INY
0.17
Tür
0.16
ISCO
0.15
ÑĢел
0.15
ÃŃny
0.15
'gc
0.14
ео
0.14
povÄĽ
0.14
جÛĮ
0.14
olson
0.14
Activations Density 0.166%