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

    Neuronpedia

    INDEX
    Explanations

    structured data or parameters in a programming context, particularly those related to functions and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somehow
    -0.15
    immel
    -0.15
    ieval
    -0.15
     Roman
    -0.15
    ellar
    -0.14
     McKay
    -0.14
    angel
    -0.14
    ucu
    -0.14
     facing
    -0.13
    app
    -0.13
    POSITIVE LOGITS
     number
    0.20
    .func
    0.19
    -function
    0.18
    function
    0.18
    number
    0.18
    string
    0.18
    object
    0.18
    .number
    0.17
     string
    0.17
     object
    0.17
    Act Density 0.040%

    No Known Activations