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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge or expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge or understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.69
    MpServer
    -0.64
    earable
    -0.62
     cropped
    -0.62
    Unix
    -0.61
    isSpecialOrderable
    -0.60
     marrow
    -0.59
    olicy
    -0.58
     sleeper
    -0.58
    ichick
    -0.58
    POSITIVE LOGITS
     Pradesh
    1.02
    ippi
    0.69
    urga
    0.63
    ä
    0.63
    dden
    0.63
    ndra
    0.62
    osi
    0.62
    cha
    0.60
    pret
    0.60
    Ñı
    0.59
    Act Density 0.242%

    No Known Activations