INDEX
Explanations
references to royalty or noble titles, particularly the term "king" and its variations
New Auto-Interp
Negative Logits
OLON
-0.16
Facade
-0.15
asil
-0.15
nic
-0.15
igans
-0.15
invert
-0.14
daÅŁ
-0.14
sector
-0.14
oon
-0.14
\Collection
-0.14
POSITIVE LOGITS
bury
0.24
Lynn
0.22
berry
0.18
bery
0.18
ley
0.18
Own
0.17
olver
0.17
College
0.17
Speech
0.16
vail
0.16
Activations Density 0.012%