INDEX
Explanations
numerical data and statistics
New Auto-Interp
Negative Logits
XV
-0.16
inka
-0.15
ocrat
-0.14
оÑĩка
-0.14
ีà¸Ļาà¸Ħม
-0.13
utdown
-0.13
ãĤ¡
-0.13
jerne
-0.13
XIII
-0.13
ãĤ¤ãĥĪ
-0.13
POSITIVE LOGITS
6
0.71
six
0.65
åħŃ
0.64
sixth
0.60
åħŃ
0.60
Six
0.58
-six
0.56
SIX
0.56
Sixth
0.56
six
0.55
Activations Density 0.084%