INDEX
Explanations
proper nouns related to families or lineage
New Auto-Interp
Negative Logits
anium
-0.17
oci
-0.15
anding
-0.15
Mime
-0.15
ANTA
-0.15
Mate
-0.15
ihn
-0.14
mate
-0.14
seau
-0.14
ICT
-0.14
POSITIVE LOGITS
çε
0.25
Lord
0.23
LORD
0.21
Lord
0.21
Baron
0.20
Lords
0.20
lord
0.20
peer
0.19
Lady
0.18
Lady
0.18
Activations Density 0.042%