INDEX
Explanations
mentions of representation and inclusion across various fields and industries
New Auto-Interp
Negative Logits
orca
-0.15
abet
-0.15
uitka
-0.15
someone
-0.14
eric
-0.14
ignet
-0.14
ieu
-0.14
ragaz
-0.14
âķ
-0.14
etÃŃ
-0.14
POSITIVE LOGITS
mainstream
0.18
745
0.15
publicly
0.14
dating
0.14
Ivy
0.13
Antar
0.13
society
0.13
Farrell
0.13
f
0.13
STEM
0.13
Activations Density 0.159%