INDEX
Explanations
references to dietary laws and restrictions
New Auto-Interp
Negative Logits
loub
-0.16
ách
-0.15
rift
-0.14
anine
-0.14
EXPECT
-0.14
Incomplete
-0.14
_salt
-0.14
ÚĨار
-0.14
obr
-0.14
isas
-0.13
POSITIVE LOGITS
ç¦ģæŃ¢
0.39
avoid
0.37
forbidden
0.36
prohibition
0.35
avoid
0.35
Avoid
0.35
prohib
0.35
avoidance
0.34
prohibited
0.34
avoided
0.34
Activations Density 0.478%