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

    Neuronpedia

    INDEX
    Explanations

    filenames or technical terms related to computer programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structure and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.78
    olute
    -0.73
    urnal
    -0.71
    ategories
    -0.70
    olson
    -0.69
    romy
    -0.69
    utch
    -0.68
    ãĤ¢ãĥ«
    -0.68
    姫
    -0.67
    otropic
    -0.67
    POSITIVE LOGITS
     portion
    0.93
     itself
    0.89
    eers
    0.85
     afore
    0.79
     USS
    0.78
     thereof
    0.76
    iest
    0.71
    osphere
    0.69
     accompanying
    0.68
    liest
    0.67
    Act Density 0.703%

    No Known Activations