INDEX
Explanations
references to originality and reproduction in creative works
New Auto-Interp
Negative Logits
rum
-0.16
upcoming
-0.14
erval
-0.14
alo
-0.14
trái
-0.13
lien
-0.13
forthcoming
-0.13
orts
-0.13
anged
-0.13
olk
-0.13
POSITIVE LOGITS
original
1.16
original
0.98
originals
0.94
Original
0.88
originally
0.86
ORIGINAL
0.85
-original
0.82
Original
0.82
(original
0.77
_original
0.77
Activations Density 0.415%