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

    Neuronpedia

    INDEX
    Explanations

    references to first ladies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRM
    -0.17
    irm
    -0.17
    uman
    -0.15
    ama
    -0.15
    ces
    -0.15
    ivas
    -0.14
    ntity
    -0.14
    ucs
    -0.14
    oge
    -0.14
    ucci
    -0.14
    POSITIVE LOGITS
    zell
    0.16
    gate
    0.15
    xCD
    0.14
    оÑĢоÑĤ
    0.14
    itives
    0.14
    ayah
    0.14
    оÑģÑĮ
    0.14
    iren
    0.14
    innie
    0.14
    ween
    0.14
    Act Density 0.009%

    No Known Activations