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

    Neuronpedia

    INDEX
    Explanations

    instances of formal address or greetings in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ķĮ
    -0.16
    .epam
    -0.14
    .persist
    -0.14
    äºĭåĭĻ
    -0.14
    thon
    -0.14
    ektiv
    -0.14
    ugo
    -0.14
    ounding
    -0.14
    iego
    -0.13
    587
    -0.13
    POSITIVE LOGITS
    apiro
    0.15
    reative
    0.15
     withhold
    0.14
    944
    0.13
    anken
    0.13
    bows
    0.13
    uem
    0.13
    /umd
    0.13
    lah
    0.13
    çķ
    0.13
    Act Density 0.003%

    No Known Activations