INDEX
Explanations
elements of design and aesthetics in vehicles
New Auto-Interp
Negative Logits
I
-0.70
I
-0.66
nobody
-0.57
why
-0.56
usually
-0.56
we
-0.56
normally
-0.56
because
-0.55
We
-0.54
because
-0.54
POSITIVE LOGITS
'),
1.03
/>";
1.02
'):
1.02
"):
1.02
'},
0.99
)";
0.97
.";
0.96
"){
0.96
'],
0.95
"),
0.95
Activations Density 0.265%