INDEX
Explanations
references to diversity, particularly in media representation
New Auto-Interp
Negative Logits
methyl
-0.59
Methyl
-0.57
Bloomsbury
-0.56
Methyl
-0.51
hatching
-0.50
amaño
-0.49
methyl
-0.49
comigo
-0.48
Roblox
-0.48
UPAC
-0.48
POSITIVE LOGITS
Marvel
1.05
MCU
1.00
Marvel
0.91
MCU
0.88
Avengers
0.87
ThroughAttribute
0.83
Avengers
0.80
marvel
0.73
Stark
0.73
Iron
0.72
Activations Density 0.155%