INDEX
Explanations
references to the Harry Potter series and its characters
New Auto-Interp
Negative Logits
jong
-0.15
onz
-0.15
ARGET
-0.15
ساÙĨ
-0.15
otto
-0.15
Cut
-0.14
.GetCurrent
-0.14
[".
-0.14
cut
-0.14
Kov
-0.14
POSITIVE LOGITS
REFER
0.15
Neutral
0.15
/ss
0.15
ups
0.15
319
0.14
aniel
0.14
Hers
0.14
Rede
0.14
s
0.14
hairs
0.14
Activations Density 0.011%