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

    Neuronpedia

    INDEX
    Explanations

    statements related to political allegations and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bapak
    -0.71
    spania
    -0.60
    ItemBackground
    -0.59
     veramente
    -0.59
    stylers
    -0.58
     secundaria
    -0.58
     Shakspeare
    -0.57
     Whilst
    -0.57
    我认为
    -0.57
    hilangan
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.60
    Напомним
    0.59
    Referències
    0.57
    WebServlet
    0.54
    ագրություններ
    0.54
     kaynağından
    0.52
     שוליים
    0.50
    Lähteet
    0.50
    Suara
    0.49
    ]}"
    0.49
    Act Density 0.090%

    No Known Activations