INDEX
Explanations
element attributes selectors
New Auto-Interp
Negative Logits
Mountains
0.50
Thoreau
0.43
Teaching
0.41
बाइक
0.40
Trail
0.39
Leaving
0.39
उल्टा
0.39
公園
0.39
Deux
0.38
åg
0.38
POSITIVE LOGITS
id
0.48
type
0.48
aria
0.47
molded
0.45
attribute
0.44
accessibility
0.44
type
0.43
context
0.43
role
0.43
атрибу
0.42
Activations Density 0.004%