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

    Neuronpedia

    INDEX
    Explanations

    references to numbers, specifically in a structured format like citations or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../../../
    -0.20
    st
    -0.20
    ../../
    -0.17
    ../../../../
    -0.16
    ptime
    -0.16
    ahan
    -0.16
    oun
    -0.16
    aso
    -0.15
     ÏĥÏįν
    -0.15
    lij
    -0.15
    POSITIVE LOGITS
    nd
    0.21
    ndx
    0.17
    ãĥ¼ãĥĦ
    0.16
    arily
    0.15
     Bundy
    0.15
    íĦ°
    0.14
    uary
    0.14
    /th
    0.14
    lsa
    0.14
    mani
    0.14
    Act Density 0.082%

    No Known Activations