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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or document in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.85
     المعيارى
    -0.79
    CPtr
    -0.66
    parsedMessage
    -0.66
     تضيفلها
    -0.65
    kloped
    -0.64
    kegaard
    -0.61
    SourceChecksum
    -0.60
     ویکی‌پدی
    -0.60
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
    </thead>
    0.58
    <h3>
    0.57
    <?
    0.55
    <h2>
    0.53
    <b>
    0.51
    <i>
    0.50
    ítése
    0.49
     wsz
    0.49
    ymce
    0.49
    renza
    0.48
    Act Density 0.151%

    No Known Activations