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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and their usage within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     صوتيه
    -1.13
     للمعارف
    -1.05
    RegressionTest
    -1.02
     ddelweddau
    -0.99
     فريبيس
    -0.95
    expandindo
    -0.92
     AssemblyTitle
    -0.91
    sizeCache
    -0.89
    abestanden
    -0.88
    saraba
    -0.86
    POSITIVE LOGITS
    p
    0.43
     suyo
    0.43
    link
    0.42
    “
    0.41
    4
    0.40
    ”
    0.40
     hijau
    0.40
    ’
    0.39
    velt
    0.39
     link
    0.38
    Act Density 0.004%

    No Known Activations