INDEX
Explanations
references to borders and crossing them
New Auto-Interp
Negative Logits
øy
-0.15
à¹Ħล
-0.14
Sparks
-0.14
íĨ¡
-0.13
InBackground
-0.13
øre
-0.13
ute
-0.13
Misc
-0.13
_misc
-0.13
Depths
-0.13
POSITIVE LOGITS
border
0.67
Border
0.54
borders
0.54
border
0.54
-border
0.50
BORDER
0.48
Border
0.48
.border
0.44
_border
0.44
border
0.41
Activations Density 0.088%