INDEX
Explanations
references to numerical data and statistical information
New Auto-Interp
Negative Logits
adh
-0.16
Kraj
-0.15
758
-0.15
urd
-0.14
asant
-0.14
oleÄį
-0.14
Gron
-0.14
ully
-0.14
onne
-0.14
Conan
-0.14
POSITIVE LOGITS
ninth
0.23
Ninth
0.22
9
0.22
Nine
0.18
ä¹Ŀ
0.17
९
0.17
nine
0.16
IX
0.16
[ix
0.16
nine
0.16
Activations Density 0.083%