INDEX
Explanations
references to Major League Baseball teams, particularly the Chicago Cubs
New Auto-Interp
Negative Logits
LayoutPanel
-0.16
ovit
-0.15
ollen
-0.14
indr
-0.14
atore
-0.14
abel
-0.14
abh
-0.14
loor
-0.14
/Layout
-0.13
ller
-0.13
POSITIVE LOGITS
anford
0.18
urdy
0.17
ugi
0.16
-generic
0.15
uire
0.15
uga
0.14
kaar
0.14
rieve
0.14
ics
0.14
ahy
0.14
Activations Density 0.011%