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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and statements, such as "print", "printf", and "Console.WriteLine"

    oai_token-act-pair · gpt-3.5-turbo

    lines of code with specific printing functions and outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chool
    -0.78
    laus
    -0.74
    arsity
    -0.71
    emis
    -0.70
    mods
    -0.70
    ipers
    -0.70
    urat
    -0.69
    OT
    -0.66
    ignty
    -0.65
    wana
    -0.65
    POSITIVE LOGITS
     "%
    0.93
     "\
    0.90
     "[
    0.86
     "$
    0.86
     "{
    0.86
     "(
    0.81
    >>>>>>>>
    0.81
     gib
    0.80
    ("
    0.79
    EO
    0.76
    Act Density 0.065%

    No Known Activations