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

    Neuronpedia

    INDEX
    Explanations

    capital letters in the middle of words

    oai_token-act-pair · gpt-3.5-turbo

    names or initials of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fet
    -0.71
     Driving
    -0.71
     RELEASE
    -0.67
     HTTPS
    -0.66
    assetsadobe
    -0.63
     Marketable
    -0.62
     wide
    -0.62
     Updates
    -0.62
     APPLIC
    -0.61
     Racial
    -0.61
    POSITIVE LOGITS
    ipp
    1.05
    iggs
    1.00
    arma
    0.97
    umble
    0.96
    utter
    0.94
    innie
    0.92
    argo
    0.92
    aud
    0.91
    uffy
    0.91
    asser
    0.89
    Act Density 0.230%

    No Known Activations