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

    Neuronpedia

    INDEX
    Explanations

    mentions of civil or civilization-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egan
    -0.18
    book
    -0.16
    egrator
    -0.15
    _NATIVE
    -0.15
    books
    -0.14
    eva
    -0.14
    ÎķΤ
    -0.14
    esis
    -0.14
    amine
    -0.14
    å¼ı
    -0.14
    POSITIVE LOGITS
    izational
    0.24
    mente
    0.20
    izations
    0.19
    isations
    0.17
    antro
    0.17
    781
    0.17
    anter
    0.17
    izing
    0.16
    اتÛĮ
    0.16
    izable
    0.16
    Act Density 0.014%

    No Known Activations