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

    Neuronpedia

    INDEX
    Explanations

    sections related to privacy and user information management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wares
    -0.15
    variant
    -0.15
    ä¼ı
    -0.15
    reu
    -0.15
    iaux
    -0.15
    _variant
    -0.15
    ']!='
    -0.15
    Å¡e
    -0.15
    hurst
    -0.14
    jadi
    -0.14
    POSITIVE LOGITS
    471
    0.17
     Pref
    0.15
     Mata
    0.14
     manual
    0.14
    sian
    0.14
     Dorm
    0.14
     toll
    0.13
    rag
    0.13
    lien
    0.13
    eman
    0.13
    Act Density 0.056%

    No Known Activations