INDEX
Explanations
names and titles of individuals in various fields such as entertainment, sports, and academia
New Auto-Interp
Negative Logits
مشين
-0.68
enschappelijke
-0.63
klant
-0.58
ChromeDriver
-0.57
subscribers
-0.56
cilind
-0.55
րջ
-0.55
AppCompat
-0.54
($__
-0.53
constituents
-0.53
POSITIVE LOGITS
writer
0.97
novelist
0.79
author
0.76
writers
0.75
photographer
0.74
poet
0.73
journalist
0.72
filmmaker
0.70
composer
0.69
noted
0.67
Activations Density 0.309%