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

    Neuronpedia

    INDEX
    Explanations

    references to options or settings within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dre
    -0.16
    outline
    -0.15
    олом
    -0.15
    _BLE
    -0.14
    Ïģε
    -0.14
    imony
    -0.14
    olls
    -0.14
    umen
    -0.14
    alo
    -0.14
    RLF
    -0.13
    POSITIVE LOGITS
    unsafe
    0.16
    ___↵↵
    0.16
    iggins
    0.15
    оÑĢов
    0.14
    ople
    0.13
    anst
    0.13
     Titles
    0.13
    /xhtml
    0.13
    arkin
    0.13
    uly
    0.13
    Act Density 0.160%

    No Known Activations