INDEX
Explanations
phrases related to childbirth and family
New Auto-Interp
Negative Logits
unts
-0.15
lef
-0.15
["$
-0.15
Intent
-0.14
tiener
-0.14
anden
-0.14
Backing
-0.14
_STAGE
-0.14
MethodInfo
-0.14
adulte
-0.14
POSITIVE LOGITS
dil
0.20
baby
0.19
born
0.19
twins
0.18
gender
0.17
twin
0.17
bouncing
0.16
baby
0.16
conceived
0.15
uze
0.15
Activations Density 0.125%