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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality or superiority in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YM
    -0.17
    Mask
    -0.15
    acists
    -0.15
    neau
    -0.15
    оген
    -0.14
    ushima
    -0.14
    ouver
    -0.14
    rvine
    -0.14
    ÑĢоÑģÑĤо
    -0.14
    ych
    -0.14
    POSITIVE LOGITS
    åħ¨éĿ¢
    0.16
    queda
    0.15
    owa
    0.14
    ivi
    0.14
    asc
    0.14
    inky
    0.14
    avin
    0.14
     Millenn
    0.14
    owing
    0.14
    ì§
    0.13
    Act Density 0.049%

    No Known Activations