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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation and formatting related to literary or official documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endregion
    -0.15
    ات
    -0.14
    hue
    -0.14
    ت
    -0.14
    aston
    -0.13
    MITTED
    -0.13
    rana
    -0.13
    aser
    -0.12
    homme
    -0.12
    lava
    -0.12
    POSITIVE LOGITS
    Ùĭ
    0.18
    à¥į
    0.18
    0.17
    à¯į
    0.17
    âĦ¢
    0.16
    καν
    0.15
    udur
    0.15
    {}
    0.14
    ument
    0.14
    asz
    0.14
    Act Density 0.377%

    No Known Activations