Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    first names

    oai_token-act-pair · gpt-3.5-turbo

    names of female characters or individuals mentioned in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sed
    -1.09
    lasses
    -0.97
    lot
    -0.96
    pan
    -0.92
    dn
    -0.92
    yg
    -0.90
    er
    -0.88
    hire
    -0.88
    erate
    -0.86
    err
    -0.86
    POSITIVE LOGITS
     Mae
    1.04
     Devi
    1.00
     Marie
    1.00
     herself
    0.96
     Grande
    0.85
    Marie
    0.80
     Louise
    0.77
     Christina
    0.77
     Fey
    0.77
     Herrera
    0.77
    Act Density 0.145%

    No Known Activations