INDEX
Explanations
references to scoring and goals in sports contexts
New Auto-Interp
Negative Logits
lak
-0.18
ocode
-0.16
fy
-0.15
bilt
-0.14
lies
-0.14
ilyn
-0.14
%+
-0.14
oland
-0.14
inish
-0.14
eya
-0.14
POSITIVE LOGITS
izont
0.15
á»ĵn
0.15
rets
0.15
å¡
0.14
θοÏĤ
0.14
оÑģ
0.14
strup
0.14
portun
0.13
fend
0.13
imal
0.13
Activations Density 0.012%