INDEX
    Explanations

    mentions of specific familial relationships, particularly involving a husband

    mentions of the word "husband."

    New Auto-Interp
    Negative Logits
    McC
    -0.76
    ortmund
    -0.71
    Import
    -0.69
    spir
    -0.68
    EVA
    -0.66
    ourcing
    -0.66
     JPM
    -0.66
     Flavoring
    -0.66
    UGE
    -0.65
    ostics
    -0.65
    POSITIVE LOGITS
    hood
    0.82
    loo
    0.79
    friend
    0.79
    pins
    0.78
    nesday
    0.77
    pin
    0.76
    husband
    0.75
    shake
    0.73
    dad
    0.72
    ry
    0.69
    Act Density 0.019%

    No Known Activations