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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or segments of code

    oai_token-act-pair · gpt-3.5-turbo

    code examples and their formatting in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saras
    -0.75
     lifes
    -0.73
    abouts
    -0.71
     furthe
    -0.70
    hement
    -0.70
     Cent
    -0.67
     Thornton
    -0.67
     Savannah
    -0.66
     emancipation
    -0.65
     neighb
    -0.65
    POSITIVE LOGITS
    <?
    1.07
    yip
    0.90
    sudo
    0.88
    Default
    0.86
    Methods
    0.85
    interface
    0.84
    #
    0.83
    template
    0.83
    Warning
    0.83
    Definition
    0.83
    Act Density 0.091%

    No Known Activations