INDEX
Explanations
references to individuals with royal titles, particularly 'King'
mentions of royalty, specifically references to kings
New Auto-Interp
Negative Logits
eria
-0.79
TING
-0.75
uated
-0.74
ename
-0.73
ciplinary
-0.72
ters
-0.71
ATIONAL
-0.68
Availability
-0.68
Ñı
-0.67
utic
-0.67
POSITIVE LOGITS
pin
1.21
uin
1.14
dom
1.13
doms
1.12
pins
1.06
fish
1.01
DOM
1.00
lord
0.91
STON
0.90
killer
0.89
Activations Density 0.015%