INDEX
Explanations
the name "Young"
mentions of the name "Young"
New Auto-Interp
Negative Logits
[]
-0.72
hex
-0.71
capitals
-0.70
enses
-0.66
domain
-0.65
tac
-0.65
gorilla
-0.63
dot
-0.63
pits
-0.62
docker
-0.62
POSITIVE LOGITS
Young
3.70
Young
3.03
young
2.33
Younger
1.85
Youth
1.71
young
1.59
Juven
1.45
youth
1.37
Teen
1.32
Older
1.31
Activations Density 0.016%