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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code formatting syntax, particularly backticks and code block delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elerik
    -0.17
    akedirs
    -0.16
    /address
    -0.14
    ktor
    -0.14
    mpeg
    -0.14
    ãģĦãģ¾ãģĻ
    -0.14
    antu
    -0.14
    úsqueda
    -0.13
    intr
    -0.13
    atura
    -0.13
    POSITIVE LOGITS
    zelf
    0.16
    illac
    0.15
    ulty
    0.15
    955
    0.15
    935
    0.15
    875
    0.15
    iously
    0.14
    conti
    0.14
    BERS
    0.14
    dez
    0.13
    Act Density 0.016%

    No Known Activations