INDEX
Explanations
proper names of people
proper names, particularly first and last names of individuals
New Auto-Interp
Negative Logits
GoldMagikarp
-0.70
ModLoader
-0.68
Fed
-0.68
CONT
-0.64
untled
-0.63
Bug
-0.62
umpy
-0.62
risome
-0.62
ubby
-0.61
VW
-0.60
POSITIVE LOGITS
sson
0.97
III
0.79
ovich
0.78
Morse
0.77
quez
0.75
enson
0.74
esc
0.69
Boyle
0.68
ovsky
0.68
enberg
0.67
Activations Density 0.150%