INDEX
Explanations
occurrences of the word "super" and its usage in code
New Auto-Interp
Negative Logits
orc
-0.18
705
-0.15
761
-0.15
corner
-0.15
489
-0.14
dto
-0.14
eder
-0.14
528
-0.14
etc
-0.14
on
-0.14
POSITIVE LOGITS
riot
0.17
vie
0.16
oton
0.15
xBD
0.15
enville
0.15
bservable
0.15
ære
0.14
UNCT
0.14
eldom
0.14
URA
0.13
Activations Density 0.003%