INDEX
    Explanations

    relationships and interactions within familial and romantic contexts

    New Auto-Interp
    Negative Logits
     Frau
    -0.30
     wife
    -0.30
     wives
    -0.29
    Ms
    -0.28
     vrouw
    -0.28
    wife
    -0.28
     woman
    -0.27
     Wife
    -0.27
    妻
    -0.27
     lady
    -0.26
    POSITIVE LOGITS
     husband
    0.52
     husbands
    0.51
     Husband
    0.48
     boyfriend
    0.46
    ä¸Ī夫
    0.44
     male
    0.41
     males
    0.39
     мÑĥж
    0.39
     hubby
    0.39
    hus
    0.38
    Act Density 0.612%

    No Known Activations