INDEX
Explanations
references to leagues or competitions in sports contexts
New Auto-Interp
Negative Logits
aceae
-0.17
serie
-0.16
soup
-0.15
Hakk
-0.15
ri
-0.14
keydown
-0.14
turned
-0.14
.Hide
-0.14
olley
-0.14
elson
-0.14
POSITIVE LOGITS
-wide
0.26
wide
0.25
-leading
0.19
/reg
0.15
Wide
0.15
/un
0.15
itti
0.15
wagon
0.15
bers
0.14
wear
0.14
Activations Density 0.013%