INDEX
Explanations
references to best-selling authors and their works
New Auto-Interp
Negative Logits
antha
-0.16
anou
-0.15
Tro
-0.15
Tro
-0.15
viso
-0.15
anka
-0.14
anship
-0.14
egrity
-0.14
qus
-0.13
zew
-0.13
POSITIVE LOGITS
best
0.84
best
0.73
Best
0.57
-best
0.56
Best
0.56
(best
0.56
bestselling
0.53
best
0.51
BEST
0.51
_best
0.50
Activations Density 0.073%