INDEX
Explanations
instances of the letter 'B' in various contexts
New Auto-Interp
Negative Logits
ureau
-0.18
ulk
-0.17
rowser
-0.17
lok
-0.17
rowse
-0.16
ullet
-0.16
ild
-0.15
/ay
-0.15
Affected
-0.15
/Dk
-0.15
POSITIVE LOGITS
linky
0.16
atsu
0.16
-side
0.15
movies
0.15
jour
0.15
word
0.14
-times
0.14
μβ
0.14
side
0.14
etimes
0.14
Activations Density 0.057%