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

    Neuronpedia

    INDEX
    Explanations

    conclusive statements or phrases indicating causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilogy
    -0.15
     <!--[
    -0.15
    ISCO
    -0.15
    duino
    -0.14
    ÙĬرا
    -0.14
    igg
    -0.14
    ccoli
    -0.14
     sor
    -0.14
    zell
    -0.14
    unj
    -0.14
    POSITIVE LOGITS
    CCA
    0.14
    lang
    0.14
    Ùħ
    0.14
    m
    0.14
    orne
    0.14
    adil
    0.13
     Baths
    0.13
    /catalog
    0.13
    ang
    0.13
    utter
    0.13
    Act Density 0.035%

    No Known Activations