INDEX
Explanations
descriptions of individuals and their characteristics
New Auto-Interp
Negative Logits
uren
-0.17
719
-0.16
chez
-0.14
vel
-0.14
aben
-0.14
Bilg
-0.14
еÑĢин
-0.14
bens
-0.14
RAIN
-0.13
agh
-0.13
POSITIVE LOGITS
medium
0.26
dark
0.23
possibly
0.23
dark
0.20
medium
0.20
Medium
0.18
possibly
0.18
Medium
0.18
Dark
0.18
darker
0.17
Activations Density 0.017%