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

    Neuronpedia

    INDEX
    Explanations

    different programming-related keywords and symbols

    oai_token-act-pair · gpt-3.5-turbo

    segments of code or functions related to data handling and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ultr
    -0.82
     patron
    -0.79
     metic
    -0.79
     Fisheries
    -0.78
     Tribal
    -0.77
     smugglers
    -0.77
     TAMADRA
    -0.77
     Byz
    -0.77
     Manit
    -0.77
     Oman
    -0.76
    POSITIVE LOGITS
    Returns
    1.56
    return
    1.55
    println
    1.53
    Output
    1.49
    else
    1.45
    assert
    1.43
    function
    1.42
    func
    1.42
    Parameters
    1.42
    static
    1.40
    Act Density 0.102%

    No Known Activations