INDEX
Explanations
proper nouns, especially names of people and sports teams
New Auto-Interp
Negative Logits
ipur
-0.17
itom
-0.17
ião
-0.15
å§ī
-0.15
æ°ijæĹı
-0.15
vore
-0.15
visa
-0.15
elia
-0.15
itself
-0.14
phinx
-0.14
POSITIVE LOGITS
Jr
0.18
Xavier
0.14
asher
0.14
nesty
0.14
Spart
0.13
III
0.13
íĴ
0.13
æĪ¶
0.13
csi
0.13
’
0.13
Activations Density 0.589%