INDEX
Explanations
references to historical lineage and significant ancestral connections
New Auto-Interp
Negative Logits
iben
-0.16
Jordan
-0.16
Yok
-0.16
keit
-0.15
Fen
-0.15
coop
-0.15
ssel
-0.15
ken
-0.14
.synthetic
-0.14
Jordan
-0.14
POSITIVE LOGITS
feud
0.21
Tip
0.20
rulers
0.19
ruler
0.19
Aur
0.18
Portuguese
0.18
ruling
0.17
naw
0.17
rule
0.17
ruled
0.17
Activations Density 0.075%