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

    Neuronpedia

    INDEX
    Explanations

    names of spouses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of wives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.91
    vernment
    -0.83
    iannopoulos
    -0.77
     dstg
    -0.74
    olkien
    -0.73
    resy
    -0.72
    tesque
    -0.72
    jriwal
    -0.71
    nyder
    -0.70
    technical
    -0.69
    POSITIVE LOGITS
     Louise
    1.40
     Isabel
    1.32
     Elizabeth
    1.31
     Marie
    1.30
     Anita
    1.29
     Nicole
    1.27
     Anne
    1.27
     Caroline
    1.27
     Claudia
    1.27
     Michelle
    1.25
    Act Density 0.171%

    No Known Activations