INDEX
Explanations
words related to royalty or authority
references to princesses and associated themes in narratives
New Auto-Interp
Negative Logits
izoph
-0.71
Peninsula
-0.71
dear
-0.63
thirds
-0.61
Psychiatry
-0.59
damn
-0.59
Harbour
-0.58
agine
-0.58
asted
-0.57
OTAL
-0.56
POSITIVE LOGITS
es
2.66
ively
1.46
esville
1.31
ed
1.31
ions
1.29
esian
1.23
esy
1.20
iveness
1.10
ecake
1.10
eson
1.09
Activations Density 0.238%