INDEX
Explanations
the name "Bruce" or variations of it
New Auto-Interp
Negative Logits
urities
-0.71
gamer
-0.68
itutional
-0.64
cycles
-0.63
orph
-0.61
ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
-0.61
agate
-0.61
dating
-0.61
Poverty
-0.60
ERA
-0.59
POSITIVE LOGITS
cker
1.06
gger
1.04
iser
1.03
nd
1.01
erk
0.99
nder
0.97
gment
0.97
cks
0.96
ggie
0.96
gging
0.96
Activations Density 0.029%