INDEX
Explanations
mentions of the name "Len"
instances of the suffix "len" in words
New Auto-Interp
Negative Logits
bulldo
-0.65
whatsoever
-0.62
package
-0.62
brought
-0.61
inevitable
-0.61
swipe
-0.61
credit
-0.61
gorilla
-0.60
boom
-0.60
mirror
-0.60
POSITIVE LOGITS
len
4.51
Len
1.89
len
1.78
lan
1.60
leneck
1.50
lon
1.45
lin
1.39
lene
1.30
ler
1.24
lers
1.23
Activations Density 0.015%