INDEX
Explanations
narratives about personal transformation and overcoming adversity
New Auto-Interp
Negative Logits
Retirement
-0.19
Stamina
-0.15
retire
-0.15
gv
-0.15
retirement
-0.15
ritz
-0.14
urd
-0.14
ühr
-0.14
buster
-0.14
roat
-0.14
POSITIVE LOGITS
gang
0.27
gangs
0.27
drugs
0.25
street
0.23
drug
0.23
drop
0.20
smoking
0.20
dropout
0.20
Drugs
0.19
GANG
0.19
Activations Density 0.109%