INDEX
Explanations
the presence of programming or technical terms related to code structure and API management
New Auto-Interp
Negative Logits
-0.74
-0.71
,
-0.69
in
-0.66
at
-0.64
a
-0.58
on
-0.56
not
-0.56
[…]
-0.56
(
-0.55
POSITIVE LOGITS
Reſ
1.18
purpoſe
1.10
ſche
1.08
Diſ
1.08
Perſ
1.05
pleaſure
1.03
houſe
1.02
perſon
1.02
Anſ
1.01
myſelf
0.99
Activations Density 1.823%