INDEX
Explanations
mentions of gendered terms, specifically related to boys and girls
New Auto-Interp
Negative Logits
mergeFrom
-0.48
EconPapers
-0.46
linkovi
-0.44
Personensuche
-0.43
Autowired
-0.43
</thead>
-0.41
när
-0.41
UnknownFields
-0.40
BeginInit
-0.38
unknownFields
-0.38
POSITIVE LOGITS
scout
0.82
scouts
0.79
Girl
0.78
Girl
0.77
Boy
0.77
boy
0.74
girl
0.73
Scouts
0.72
Scout
0.68
Boy
0.68
Activations Density 0.092%