INDEX
Explanations
HTML or JSX elements including opening and closing tags
New Auto-Interp
Negative Logits
agara
-0.20
wright
-0.15
wald
-0.15
077
-0.15
quez
-0.14
ModelIndex
-0.14
-navbar
-0.14
irie
-0.14
oplay
-0.14
mind
-0.14
POSITIVE LOGITS
div
0.43
div
0.40
span
0.31
span
0.29
ul
0.28
-div
0.27
divers
0.25
.div
0.24
Div
0.24
div
0.23
Activations Density 0.043%