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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     дописавши
    -0.66
    رشف
    -0.57
     ComVisible
    -0.57
    pidou
    -0.55
    plc
    -0.50
    Wikis
    -0.48
    konos
    -0.47
    าสตร์
    -0.47
     femininos
    -0.47
    らし
    -0.47
    POSITIVE LOGITS
     оригіналу
    0.66
    Rég
    0.64
    etheless
    0.61
    \|_{\
    0.61
    manent
    0.58
     "..\..\
    0.55
    \|_{
    0.53
    ArrowToggle
    0.53
    HostException
    0.53
    bulk
    0.51
    Act Density 0.017%

    No Known Activations