INDEX
Explanations
references to open source software and education-related projects
New Auto-Interp
Negative Logits
bis
-0.17
grund
-0.16
anne
-0.15
ournals
-0.14
onte
-0.14
pins
-0.14
å¨ĺ
-0.14
ENU
-0.14
cona
-0.14
ham
-0.13
POSITIVE LOGITS
/open
0.23
-source
0.23
-ended
0.22
source
0.20
/free
0.20
/Open
0.20
Source
0.19
setOpen
0.18
ended
0.18
baar
0.18
Activations Density 0.020%