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

    Neuronpedia

    INDEX
    Explanations

    elements related to authorship, editing, and the presentation of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.17
    ziej
    -0.15
    ully
    -0.14
    egot
    -0.14
    rent
    -0.14
    ãĤ´ãĥª
    -0.14
    afi
    -0.14
    .destroy
    -0.13
    ãĥ¼ãĥĬ
    -0.13
    /ajax
    -0.13
    POSITIVE LOGITS
    chap
    0.18
    wap
    0.16
    undle
    0.16
    dap
    0.15
    maz
    0.14
    dol
    0.14
    ondon
    0.14
    RIA
    0.14
    quires
    0.14
    illon
    0.14
    Act Density 0.014%

    No Known Activations