INDEX
Explanations
mentions of relationships and family connections
New Auto-Interp
Negative Logits
strup
-0.17
pson
-0.16
arten
-0.15
uco
-0.15
ovit
-0.15
ocos
-0.14
alon
-0.14
obo
-0.14
mai
-0.14
Rooney
-0.14
POSITIVE LOGITS
me
0.26
myself
0.23
æĪij
0.17
I
0.17
us
0.17
anka
0.16
mij
0.16
_aa
0.15
HQ
0.15
mgr
0.15
Activations Density 0.031%