INDEX
Explanations
descriptions related to physical appearance
descriptors related to physical appearance
New Auto-Interp
Negative Logits
chat
-0.81
elo
-0.81
ocrates
-0.80
lvl
-0.77
clair
-0.76
alter
-0.76
aucus
-0.75
trak
-0.74
ontent
-0.74
ARS
-0.73
POSITIVE LOGITS
voices
0.75
neoc
0.73
ones
0.73
professions
0.72
occupations
0.72
subsequ
0.72
compositions
0.72
fug
0.71
pursuits
0.71
goods
0.70
Activations Density 0.071%