INDEX
    Explanations

    phrases related to consent and personal relationships

    New Auto-Interp
    Negative Logits
     granddaughter
    -0.17
     Babies
    -0.17
    asco
    -0.16
    azzi
    -0.15
     grandson
    -0.15
    reta
    -0.15
    baby
    -0.15
    zym
    -0.14
     newborn
    -0.14
    Baby
    -0.14
    POSITIVE LOGITS
     parents
    0.77
     Parents
    0.66
     parent
    0.65
    parents
    0.63
    Parents
    0.60
     parental
    0.54
    parent
    0.53
    -parent
    0.51
     Parent
    0.50
    _parents
    0.50
    Act Density 0.341%

    No Known Activations