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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "read" and associated phrases indicating scrolling or continuing to view content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    енÑĮ
    -0.18
    dam
    -0.16
    PIO
    -0.15
    okol
    -0.15
    /renderer
    -0.14
    crast
    -0.14
    akest
    -0.14
    /callback
    -0.14
    TEM
    -0.14
    arrison
    -0.14
    POSITIVE LOGITS
    andes
    0.17
    ourg
    0.16
    iyat
    0.14
    153
    0.14
    ripp
    0.14
    Lon
    0.14
    resi
    0.14
     Haus
    0.14
     Bert
    0.13
    롱
    0.13
    Act Density 0.019%

    No Known Activations