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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orie
    -0.17
    Äįet
    -0.15
    ses
    -0.15
    odore
    -0.15
    heid
    -0.14
    rie
    -0.14
    ãĥ¼ãĤ
    -0.13
    rint
    -0.13
    arms
    -0.13
    leri
    -0.13
    POSITIVE LOGITS
    ï¸ı
    0.16
    ãģĹãģªãģĦ
    0.16
    ä¸ŃæĸĩåŃĹå¹ķ
    0.15
    ;element
    0.15
    /=
    0.15
    ····
    0.15
    ÑĶм
    0.14
    /OR
    0.14
    chandle
    0.13
    kola
    0.13
    Act Density 0.089%

    No Known Activations