INDEX
Explanations
proper nouns or names with the string "Ben" in them
the name "Ben" and its occurrences in various contexts
New Auto-Interp
Negative Logits
perse
-0.66
inarily
-0.66
mson
-0.66
REDACTED
-0.64
hower
-0.63
Artist
-0.62
ngth
-0.62
DragonMagazine
-0.61
Oper
-0.61
RNA
-0.60
POSITIVE LOGITS
jamin
1.60
nington
1.17
oit
1.17
ghazi
0.97
cher
0.91
imaru
0.90
chers
0.90
ito
0.85
ning
0.83
ches
0.83
Activations Density 0.019%