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

    Neuronpedia

    INDEX
    Explanations

    references to family members, specifically grandmothers

    oai_token-act-pair · gpt-3.5-turbo

    references to grandmothers or related family figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oned
    -0.82
    gged
    -0.79
    assic
    -0.75
    axis
    -0.75
    nces
    -0.74
    yss
    -0.72
    oning
    -0.72
    etheus
    -0.72
    asing
    -0.70
    uchin
    -0.69
    POSITIVE LOGITS
     grandmother
    1.03
     aunt
    0.97
     grandma
    0.96
    mother
    0.91
    father
    0.86
    sburgh
    0.85
    stones
    0.79
    arten
    0.77
     Carolyn
    0.74
    parents
    0.74
    Act Density 0.012%

    No Known Activations