INDEX
Explanations
names and titles related to royalty
references to historical or fictional kings
New Auto-Interp
Negative Logits
Helpful
-0.82
ocre
-0.78
alore
-0.77
resso
-0.72
inarily
-0.71
nyder
-0.70
abus
-0.70
aminer
-0.70
selves
-0.70
alyst
-0.69
POSITIVE LOGITS
ij士
0.88
throne
0.81
Honour
0.79
çİĭ
0.75
ãĤ´ãĥ³
0.75
jong
0.73
XIV
0.73
XVI
0.73
recognise
0.72
Majesty
0.72
Activations Density 0.184%