INDEX
Explanations
references to wooden materials and objects
New Auto-Interp
Negative Logits
eÄį
-0.17
eut
-0.16
linkplain
-0.15
otu
-0.14
Stones
-0.14
epam
-0.14
egot
-0.14
onaut
-0.14
æľį
-0.14
loose
-0.14
POSITIVE LOGITS
bine
0.22
chip
0.20
licken
0.16
plank
0.16
sworth
0.16
shed
0.16
-fr
0.15
erner
0.15
unny
0.15
zas
0.15
Activations Density 0.016%