INDEX
Explanations
references to infant care and child-rearing activities
New Auto-Interp
Negative Logits
endra
-0.16
ascus
-0.16
pra
-0.15
ãĥ¬ãĥ¼
-0.15
ä¼į
-0.14
.idx
-0.14
_OID
-0.14
tember
-0.13
NIL
-0.13
UnderTest
-0.13
POSITIVE LOGITS
ooks
0.16
obao
0.14
gu
0.14
peaker
0.14
Warner
0.14
ÑĢÑĥж
0.14
tout
0.14
acker
0.14
/people
0.14
sb
0.13
Activations Density 0.050%