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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antu
    -0.17
    ogne
    -0.15
    rang
    -0.15
    sdale
    -0.14
    ibur
    -0.14
    ascular
    -0.14
    thro
    -0.13
    ovÄĽ
    -0.13
    otty
    -0.13
    _("
    -0.13
    POSITIVE LOGITS
    ãĢħ
    0.16
    rens
    0.15
    gni
    0.15
    leta
    0.15
    áºŃt
    0.15
    -centered
    0.14
    sert
    0.14
    rosse
    0.14
    oji
    0.14
    antry
    0.14
    Act Density 0.169%

    No Known Activations