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

    Neuronpedia

    INDEX
    Explanations

    the beginning of textual sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    漓
    -0.47
     vak
    -0.46
    fre
    -0.46
     fundamental
    -0.44
    Gemeinsame
    -0.44
    prising
    -0.43
    Má
    -0.43
    isins
    -0.41
    sys
    -0.41
    tev
    -0.41
    POSITIVE LOGITS
    <bos>
    0.85
      (
    0.69
     ویکی‌پدیا
    0.68
    RegressionTest
    0.67
    0.65
     Савезне
    0.65
     autorytatywna
    0.65
    PyExc
    0.64
     дописавши
    0.64
     виправивши
    0.62
    Act Density 0.000%

    No Known Activations