INDEX
Explanations
ISBN numbers and bibliographic information related to books
New Auto-Interp
Negative Logits
esub
-0.18
umbnails
-0.14
_Abstract
-0.14
ije
-0.14
æĶ¯
-0.14
encil
-0.14
íĹ
-0.13
stÃŃ
-0.13
abstract
-0.13
uw
-0.13
POSITIVE LOGITS
Harper
0.20
audi
0.18
Audio
0.18
Audio
0.18
audio
0.17
AUDIO
0.17
hoop
0.16
novel
0.15
audio
0.15
Reader
0.15
Activations Density 0.109%