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

    Neuronpedia

    INDEX
    Explanations

    triggers and phrases indicating a call to action or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ŀ
    -0.15
    viz
    -0.15
    raquo
    -0.14
    CDATA
    -0.14
    ptime
    -0.14
    abbit
    -0.14
    alice
    -0.14
    oron
    -0.14
    ivant
    -0.14
    amura
    -0.14
    POSITIVE LOGITS
    ossal
    0.15
    laÅŁ
    0.15
    ë²Ķ
    0.14
    ONES
    0.14
    lag
    0.14
     potentially
    0.13
    frog
    0.13
    CustomAttributes
    0.13
    stown
    0.13
    oard
    0.13
    Act Density 0.462%

    No Known Activations