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

    Neuronpedia

    INDEX
    Explanations

    variables, functions, and code snippets within a programming context

    oai_token-act-pair · gpt-3.5-turbo

    function and variable definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.80
     Institution
    -0.79
     Opportun
    -0.78
     Constitutional
    -0.68
    CLASSIFIED
    -0.68
    ×Ļ×
    -0.68
     crucifix
    -0.67
     Disorder
    -0.67
    ãĤª
    -0.66
    éļ
    -0.66
    POSITIVE LOGITS
    args
    0.87
    dx
    0.84
    seq
    0.83
    db
    0.83
    stack
    0.82
    code
    0.78
    cs
    0.77
    pi
    0.77
    vp
    0.76
    copy
    0.75
    Act Density 0.147%

    No Known Activations