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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their significance in text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifax
    -0.15
    jde
    -0.14
    ibase
    -0.14
    alah
    -0.14
     jos
    -0.13
    ë¡Ģ
    -0.13
    ÑĭÑģ
    -0.13
    plete
    -0.13
    ichni
    -0.13
    .liferay
    -0.13
    POSITIVE LOGITS
    uard
    0.16
    geois
    0.15
    ãģ¾ãģ¾
    0.15
    OfYear
    0.14
    ewart
    0.14
    uthor
    0.13
    rown
    0.13
    atorio
    0.13
    amma
    0.13
    amm
    0.13
    Act Density 0.390%

    No Known Activations