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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain identifiers within programming or text elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.20
    strup
    -0.19
    cia
    -0.16
    lest
    -0.16
    æk
    -0.14
    ngör
    -0.14
    AREST
    -0.14
    Manifest
    -0.14
    /Peak
    -0.14
    Deck
    -0.14
    POSITIVE LOGITS
     Pat
    0.17
     Gross
    0.16
     Scroll
    0.16
    ropp
    0.16
    Unnamed
    0.15
     scroll
    0.15
    scroll
    0.15
    KERNEL
    0.14
     scrolls
    0.14
     Jud
    0.14
    Act Density 0.019%

    No Known Activations