INDEX
Explanations
references to the Los Angeles Dodgers baseball team
references to the Dodgers baseball team
New Auto-Interp
Negative Logits
lying
-0.87
uters
-0.82
awaru
-0.80
eatures
-0.76
neau
-0.75
ilities
-0.73
gomery
-0.72
oppable
-0.72
autical
-0.72
lopp
-0.71
POSITIVE LOGITS
Dodgers
0.96
Padres
0.84
Stadium
0.81
pitcher
0.72
Baseball
0.72
Seal
0.71
Republic
0.68
outfielder
0.68
reliever
0.66
Hots
0.64
Activations Density 0.012%