INDEX
Explanations
references to utopias and dystopias
terms related to utopian or dystopian concepts and locations
New Auto-Interp
Negative Logits
agers
-0.85
asp
-0.77
aging
-0.77
aged
-0.77
writers
-0.76
nell
-0.73
aunt
-0.72
work
-0.71
ney
-0.70
angers
-0.66
POSITIVE LOGITS
opia
0.97
ternity
0.94
eus
0.93
onia
0.91
ħĭ
0.88
edia
0.87
ea
0.84
unia
0.80
Scotia
0.80
Borders
0.79
Activations Density 0.025%