INDEX
Explanations
HTML unordered list elements
New Auto-Interp
Negative Logits
Brandenburg
-0.77
<b>
-0.67
став
-0.64
lccc
-0.64
дин
-0.64
__["
-0.64
a
-0.63
Clara
-0.61
Gries
-0.61
BNB
-0.59
POSITIVE LOGITS
ul
1.46
ul
1.17
UL
1.14
Ul
1.09
UL
0.99
ulcers
0.96
Ul
0.95
عليكم
0.90
ulx
0.87
Eul
0.86
Activations Density 0.038%