INDEX
Explanations
elements related to interpersonal relationships and societal connections
New Auto-Interp
Negative Logits
quate
-0.14
ÅĻÃŃ
-0.14
ulfilled
-0.14
رÙĪØ¹
-0.14
Forg
-0.14
šem
-0.14
_softc
-0.13
uzey
-0.13
#af
-0.13
ognition
-0.13
POSITIVE LOGITS
lekker
0.21
kind
0.20
tieten
0.20
meiden
0.19
Kind
0.18
vriend
0.18
mooie
0.18
av
0.17
spoken
0.17
pr
0.17
Activations Density 0.058%