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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating parameters or settings in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    if
    -0.36
    int
    -0.28
    C
    -0.28
    S
    -0.27
    get
    -0.27
    P
    -0.26
    for
    -0.26
     ↵
    -0.26
    G
    -0.25
    R
    -0.25
    POSITIVE LOGITS
    //
    0.17
    /*↵
    0.13
    shift
    0.13
    storage
    0.13
    shadow
    0.12
    //↵
    0.12
    pro
    0.12
    wh
    0.12
    home
    0.12
    /**↵
    0.12
    Act Density 0.186%

    No Known Activations