INDEX
Explanations
references to familial relationships, particularly involving parents and children
New Auto-Interp
Negative Logits
semb
-0.15
angs
-0.15
oso
-0.15
phis
-0.15
tek
-0.15
.dm
-0.14
ospel
-0.14
income
-0.14
_income
-0.14
Peg
-0.13
POSITIVE LOGITS
LIN
0.16
lev
0.15
iece
0.15
庫
0.14
icer
0.14
cu
0.14
ooter
0.13
upper
0.13
LOTS
0.13
]|[
0.13
Activations Density 0.211%