INDEX
Explanations
themes related to family dynamics and adoption
New Auto-Interp
Negative Logits
enso
-0.17
ancestor
-0.16
klass
-0.16
ety
-0.15
corrid
-0.15
YNC
-0.14
ạ
-0.14
_cg
-0.13
ofire
-0.13
rub
-0.13
POSITIVE LOGITS
oyer
0.16
morb
0.15
Institution
0.14
ì±ħ
0.14
èŃ
0.14
onyms
0.14
rone
0.13
ären
0.13
Pair
0.13
èĹ
0.13
Activations Density 0.085%