INDEX
Explanations
mentions of books or literature
New Auto-Interp
Negative Logits
ept
-0.17
monds
-0.17
booking
-0.17
mons
-0.16
igm
-0.15
brook
-0.15
_booking
-0.15
esModule
-0.15
economic
-0.15
bookings
-0.15
POSITIVE LOGITS
shelf
0.40
ç±į
0.36
ends
0.32
worm
0.32
stores
0.31
keeping
0.31
lets
0.29
azine
0.29
ish
0.28
shop
0.28
Activations Density 0.073%