INDEX
Explanations
references to the platform GitHub
references to GitHub and its related functionalities
New Auto-Interp
Negative Logits
phe
-0.80
eal
-0.74
ibus
-0.73
phal
-0.68
thritis
-0.67
igm
-0.64
̶
-0.63
eed
-0.62
zzi
-0.62
igslist
-0.62
POSITIVE LOGITS
GitHub
1.05
repository
1.04
repositories
0.93
repo
0.88
Github
0.84
Pages
0.84
github
0.77
Mellon
0.74
usercontent
0.73
wik
0.73
Activations Density 0.009%