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

    Neuronpedia

    INDEX
    Explanations

    significant phrases and high-frequency function words that structure the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulls
    -0.17
    gne
    -0.16
    ÑĨÑİ
    -0.16
    arde
    -0.15
    cta
    -0.14
    ierce
    -0.14
    azo
    -0.14
    )?$
    -0.14
    581
    -0.13
    -Ray
    -0.13
    POSITIVE LOGITS
     Mang
    0.17
    uzzi
    0.16
    itzer
    0.15
    uma
    0.15
    PEND
    0.15
    /umd
    0.15
     enc
    0.14
    Kit
    0.14
    fast
    0.14
    ngine
    0.14
    Act Density 0.007%

    No Known Activations