INDEX
Explanations
expressions related to familial and relational dynamics
New Auto-Interp
Negative Logits
otu
-0.16
elor
-0.15
ebb
-0.15
LLU
-0.14
å²Ĺ
-0.14
atre
-0.14
536
-0.14
isco
-0.14
ew
-0.14
ÛĢ
-0.14
POSITIVE LOGITS
shared
0.24
åħ±åIJĮ
0.23
shared
0.22
jointly
0.21
.shared
0.21
Shared
0.21
gemeins
0.21
mutual
0.20
_shared
0.20
joint
0.20
Activations Density 0.006%