INDEX
Explanations
references to childbirth and related experiences
New Auto-Interp
Negative Logits
Brennan
-0.18
ุà¹Ī
-0.18
ifa
-0.16
Inherits
-0.15
uni
-0.15
unborn
-0.15
ackbar
-0.15
راÙĨÛĮ
-0.15
é©
-0.14
rella
-0.14
POSITIVE LOGITS
delivery
0.40
Delivery
0.33
birth
0.33
delivery
0.32
deliveries
0.32
Delivery
0.31
labor
0.30
bir
0.30
labour
0.29
giving
0.28
Activations Density 0.050%