INDEX
Explanations
proper nouns related to sports teams, political affiliations, and occupations
New Auto-Interp
Negative Logits
/proto
-0.15
Closure
-0.14
bour
-0.14
θι
-0.14
reffen
-0.14
MotionEvent
-0.14
Serif
-0.13
:"-"`↵
-0.13
unos
-0.13
oine
-0.13
POSITIVE LOGITS
dit
0.14
May
0.14
Ok
0.14
Henry
0.14
Rap
0.13
Shar
0.13
OK
0.13
DD
0.13
Pr
0.13
Ñĥка
0.13
Activations Density 0.057%