INDEX
    Explanations

    references to a specific female individual in different contexts or situations

    references to a specific individual, particularly in relation to events or actions involving that person

    New Auto-Interp
    Negative Logits
    ype
    -0.88
    ypes
    -0.85
    ozy
    -0.82
    kefeller
    -0.80
    arios
    -0.80
    eers
    -0.79
    ornia
    -0.78
    ablishment
    -0.76
    eering
    -0.74
    uminati
    -0.69
    POSITIVE LOGITS
     own
    1.32
    ding
    1.20
     daughter
    1.10
    metic
    1.08
    cule
    1.05
     granddaughter
    1.04
     Majesty
    1.04
     husband
    1.03
    itage
    0.99
     sister
    0.99
    Act Density 0.108%

    No Known Activations