INDEX
Explanations
mentions of the Oscars and related award categories
New Auto-Interp
Negative Logits
azor
-0.15
kem
-0.14
733
-0.14
WARRANT
-0.14
Thumb
-0.14
ÑģÑĤвоÑĢ
-0.14
OKIE
-0.14
bay
-0.14
bay
-0.14
pilot
-0.14
POSITIVE LOGITS
Academy
0.33
Oscars
0.28
Oscar
0.28
academy
0.27
acad
0.23
Motion
0.21
osc
0.20
Motion
0.19
Osc
0.19
nominees
0.18
Activations Density 0.036%