INDEX
Explanations
professional roles or occupations
New Auto-Interp
Negative Logits
edin
-0.79
apo
-0.76
attr
-0.72
anus
-0.67
_>
-0.66
ource
-0.66
adr
-0.66
bolt
-0.65
pots
-0.65
tags
-0.65
POSITIVE LOGITS
wrestler
1.05
athlete
0.99
athletes
0.95
gol
0.93
footballer
0.93
wrestling
0.92
digy
0.92
ized
0.90
ising
0.86
Wrest
0.84
Activations Density 0.059%