INDEX
Explanations
terms related to babies and baby products
New Auto-Interp
Negative Logits
rd
-0.17
wart
-0.16
uforia
-0.16
iap
-0.15
battle
-0.14
fully
-0.14
-speaking
-0.14
ality
-0.14
ampo
-0.14
isions
-0.13
POSITIVE LOGITS
hood
0.24
/small
0.22
/new
0.17
oni
0.17
doll
0.16
-sized
0.16
/people
0.16
folio
0.16
-size
0.14
/mat
0.14
Activations Density 0.028%