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

    Neuronpedia

    INDEX
    Explanations

    names of authors and relevant publication details

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.96
     وتسجيلات
    -0.96
     للمعارف
    -0.91
     كومونز
    -0.88
    Datuak
    -0.88
    XmlAccessType
    -0.87
    expandindo
    -0.84
     AssemblyCompany
    -0.82
    انيف
    -0.81
     متعلقه
    -0.77
    POSITIVE LOGITS
    Климат
    0.49
    v
    0.46
    <eos>
    0.45
    ())),
    0.42
    (.
    0.40
    pp
    0.40
     Buren
    0.40
    车
    0.40
    ber
    0.39
    ()));
    0.38
    Act Density 0.207%

    No Known Activations