INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
grandson
0.55
father
0.52
father
0.51
nephew
0.46
godfather
0.46
female
0.45
experienced
0.44
wife
0.44
daughter
0.43
handsome
0.43
POSITIVE LOGITS
responsáveis
0.48
働
0.47
负责
0.45
එහි
0.44
Xaml
0.44
xon
0.43
مسئ
0.43
𝙃
0.43
অংশের
0.42
bertanggung
0.41
Activations Density 0.003%