INDEX
Explanations
mentions of rights and entitlements in a legal or social context
New Auto-Interp
Negative Logits
IP
-0.16
ساز
-0.15
ritch
-0.14
ritte
-0.14
iah
-0.14
بار
-0.14
ogle
-0.13
è¥
-0.13
acro
-0.13
hek
-0.13
POSITIVE LOGITS
atas
0.15
×Ĺ
0.14
atform
0.14
rus
0.14
eous
0.13
prov
0.13
Blanch
0.13
ACHI
0.13
ears
0.13
swire
0.13
Activations Density 0.020%