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

    Neuronpedia

    INDEX
    Explanations

    specific instances of café and decorative terms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyla
    -0.17
    ı
    -0.14
    BST
    -0.14
    ace
    -0.13
    iest
    -0.13
    iano
    -0.13
    inho
    -0.13
    ously
    -0.13
    rell
    -0.13
    ä¸ĢåĮº
    -0.13
    POSITIVE LOGITS
    ï¸ı
    0.40
    ï¸
    0.29
    elsius
    0.23
    erif
    0.20
    âĨĴâĨĴ
    0.19
    teborg
    0.19
    ever
    0.18
    dür
    0.18
    Ù«
    0.18
    lico
    0.18
    Act Density 0.165%

    No Known Activations