INDEX
Explanations
ages of individuals
references to age, specifically numeric age descriptions
New Auto-Interp
Negative Logits
Bundy
-0.69
earances
-0.68
DCS
-0.68
eries
-0.68
vernment
-0.67
atari
-0.66
edia
-0.66
aptic
-0.64
pmwiki
-0.63
overlook
-0.58
POSITIVE LOGITS
18
0.90
19
0.88
21
0.87
23
0.84
13
0.81
15
0.81
16
0.80
22
0.80
25
0.80
14
0.79
Activations Density 0.038%