INDEX
Explanations
references to authorship and manuscripts in literature
New Auto-Interp
Negative Logits
azzo
-0.16
icari
-0.16
ijd
-0.15
":"/
-0.14
onds
-0.14
achuset
-0.14
disposed
-0.14
apon
-0.14
μί
-0.14
osta
-0.14
POSITIVE LOGITS
attrib
0.20
attribution
0.19
attrib
0.18
attributed
0.18
Attrib
0.18
orch
0.16
credited
0.16
author
0.15
ownership
0.15
anonymous
0.15
Activations Density 0.199%