INDEX
Explanations
phrases related to parenthood and family dynamics
New Auto-Interp
Negative Logits
grandchildren
-0.19
Brothers
-0.17
siblings
-0.17
brothers
-0.17
aku
-0.16
Buccane
-0.16
idar
-0.15
sibling
-0.15
ighth
-0.15
åīį
-0.15
POSITIVE LOGITS
baby
0.30
baby
0.25
infant
0.24
Baby
0.23
Baby
0.22
newborn
0.21
babies
0.20
infants
0.18
Infant
0.17
BAB
0.17
Activations Density 0.087%