INDEX
Explanations
instances of the letter "B" in various forms and contexts
New Auto-Interp
Negative Logits
ara
-0.19
BB
-0.18
оÑĢ
-0.18
ern
-0.18
yy
-0.18
oe
-0.18
ru
-0.18
uf
-0.17
io
-0.17
ounder
-0.17
POSITIVE LOGITS
em
0.25
im
0.23
ong
0.22
antu
0.20
enth
0.20
oll
0.19
AN
0.19
ony
0.19
bread
0.19
hop
0.19
Activations Density 0.215%