INDEX
Explanations
references to Black individuals or the concept of blackness in various contexts
references to race, specifically the word "black" and related racial terminology.
New Auto-Interp
Negative Logits
AssemblyCompany
-0.71
fjspx
-0.63
Pov
-0.57
vibe
-0.57
Vibe
-0.57
Rptr
-0.57
müſſen
-0.56
προς
-0.56
Cyfarwyddwr
-0.56
ukunft
-0.56
POSITIVE LOGITS
Black
1.23
Black
1.19
BLACK
1.13
black
1.13
black
1.06
BLACK
1.03
schwarze
0.77
zwarte
0.74
Blacks
0.74
黑
0.73
Activations Density 0.040%