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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å£°éŁ³
    -0.07
    ubb
    -0.07
     otherwise
    -0.07
    mise
    -0.06
    veh
    -0.06
    erli
    -0.06
    edy
    -0.06
    olit
    -0.06
    /errors
    -0.06
    ↵
    -0.06
    POSITIVE LOGITS
    /'
    0.10
    ÂĿ
    0.09
    |"
    0.08
    ãĢģ“
    0.08
    buster
    0.07
    aint
    0.07
    ych
    0.07
    _-_
    0.07
    ÑĪÑĤов
    0.07
    -"
    0.07
    Act Density 0.067%

    No Known Activations