INDEX
    Explanations

    mentions of family relationships, particularly focusing on daughters

    mentions of family relationships, specifically focusing on daughters

    New Auto-Interp
    Negative Logits
    kefeller
    -0.84
     constitu
    -0.76
     dstg
    -0.75
    ilitarian
    -0.68
    uchin
    -0.66
    etting
    -0.65
    ioxide
    -0.64
    hent
    -0.63
    ypes
    -0.63
    vernment
    -0.63
    POSITIVE LOGITS
     Ivanka
    0.87
     daughter
    0.85
    Anne
    0.80
     daughters
    0.80
     Isabel
    0.78
    daughter
    0.78
     Louise
    0.77
    hood
    0.77
    Maria
    0.76
    ishly
    0.76
    Act Density 0.015%

    No Known Activations