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

    Neuronpedia

    INDEX
    Explanations

    references to code segments or snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    name
    -0.16
    w
    -0.16
    ss
    -0.16
    so
    -0.15
    lay
    -0.15
    /desktop
    -0.15
    most
    -0.15
    requ
    -0.14
    lah
    -0.14
    wf
    -0.14
    POSITIVE LOGITS
    velopment
    0.23
    段
    0.20
    碼
    0.19
    base
    0.18
    (Code
    0.18
    åĿĹ
    0.18
    pend
    0.18
    villa
    0.17
    иÑĢов
    0.17
    book
    0.17
    Act Density 0.022%

    No Known Activations