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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols used in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    عاد
    -0.16
    ial
    -0.16
    ing
    -0.15
    ÅĻe
    -0.15
    asing
    -0.14
    ered
    -0.14
    оÑģп
    -0.14
    ere
    -0.14
    bdd
    -0.14
    ей
    -0.14
    POSITIVE LOGITS
    ÂĢÂĻ
    0.20
    âĤ¬âĦ¢
    0.18
    mega
    0.18
    metro
    0.17
    ÂĢÂ
    0.17
    lico
    0.17
    minus
    0.16
    nia
    0.15
    mb
    0.15
    زر
    0.15
    Act Density 0.019%

    No Known Activations