INDEX
Explanations
references to childbirth and maternal experiences
New Auto-Interp
Negative Logits
ibel
-0.15
ughs
-0.15
ione
-0.15
umat
-0.15
Bib
-0.14
ernel
-0.14
ायल
-0.14
inho
-0.14
Emb
-0.14
unga
-0.13
POSITIVE LOGITS
delivery
0.47
Delivery
0.44
deliveries
0.43
Delivery
0.38
delivery
0.38
birth
0.36
delivering
0.35
Deliver
0.35
deliver
0.35
deliver
0.34
Activations Density 0.073%