INDEX
Explanations
descriptions or characteristics of physical objects and their arrangements
New Auto-Interp
Negative Logits
reira
-0.16
odont
-0.14
.maps
-0.14
etto
-0.13
position
-0.13
æŁ±
-0.13
iyet
-0.13
indow
-0.13
arra
-0.13
ley
-0.13
POSITIVE LOGITS
sides
0.56
edges
0.54
ends
0.43
corners
0.41
edges
0.40
Edges
0.36
margins
0.33
borders
0.33
_edges
0.33
(edges
0.32
Activations Density 0.289%