INDEX
Explanations
references to notable sports figures and their achievements
New Auto-Interp
Negative Logits
alth
-0.17
duk
-0.16
simp
-0.16
lette
-0.15
rames
-0.15
das
-0.15
^-
-0.14
inspace
-0.14
thur
-0.14
dee
-0.14
POSITIVE LOGITS
zcze
0.17
bark
0.15
imi
0.14
Dillon
0.14
bl
0.14
Bark
0.13
Lindsay
0.13
abcdefghijklmnop
0.13
ova
0.13
haci
0.13
Activations Density 0.249%