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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical information

    oai_token-act-pair · gpt-3.5-turbo

    special characters, numbers, and formatting indicators typically seen in structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.96
    ĺħ
    -0.83
    xon
    -0.78
    tsky
    -0.67
    ospace
    -0.63
    idth
    -0.63
    aturdays
    -0.63
     fold
    -0.63
    ngth
    -0.62
    hesda
    -0.61
    POSITIVE LOGITS
    ":{"
    1.02
    ":[{"
    0.96
    ãĥĻ
    0.93
    ":["
    0.92
    Buyable
    0.91
    ":"
    0.89
    channelAvailability
    0.87
    ":[
    0.85
    ?????-
    0.80
    ä
    0.80
    Act Density 0.100%

    No Known Activations