INDEX
Explanations
mentions of military service and related experiences
New Auto-Interp
Negative Logits
elan
-0.16
borg
-0.16
Seymour
-0.16
ÙĬدÙĬ
-0.15
iven
-0.15
velt
-0.15
umi
-0.14
Flesh
-0.14
ird
-0.14
breadcrumbs
-0.14
POSITIVE LOGITS
été
0.15
Uniform
0.15
oggled
0.15
uniform
0.15
942
0.14
Uniform
0.14
ëıĻ
0.14
nowrap
0.14
merc
0.14
æ£Ĵ
0.14
Activations Density 0.051%