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

    Neuronpedia

    INDEX
    Explanations

    words related to legal terminology and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rollers
    -0.16
    Ñĩи
    -0.15
    wy
    -0.14
    anmar
    -0.14
    аÑĢÑĤ
    -0.14
    feld
    -0.14
    ored
    -0.14
    ÑĶм
    -0.14
    _TEX
    -0.13
    erna
    -0.13
    POSITIVE LOGITS
    度
    0.16
    opor
    0.16
    оÑĢе
    0.15
    etta
    0.15
    анÑģов
    0.14
    979
    0.13
    æĽľ
    0.13
    lue
    0.13
    ë¥
    0.13
    aight
    0.13
    Act Density 0.027%

    No Known Activations