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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to programming and compiling code

    oai_token-act-pair · gpt-3.5-turbo

    terms related to program compilation processes in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.79
    erville
    -0.77
    phasis
    -0.77
    Ĥª
    -0.76
    holes
    -0.74
    atos
    -0.73
    arat
    -0.71
    ricular
    -0.71
    laus
    -0.70
    lyak
    -0.70
    POSITIVE LOGITS
     compiled
    0.77
     gcc
    0.77
     compilation
    0.75
    ilers
    0.75
    uration
    0.73
     errors
    0.72
     error
    0.70
    strap
    0.69
     compiler
    0.69
    SON
    0.69
    Act Density 0.075%

    No Known Activations