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

    Neuronpedia

    INDEX
    Explanations

    sections or indicators in text denoting non-active content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -1.03
     himo
    -0.91
    ']))
    -0.90
    `,
    -0.85
    '],
    -0.82
    **/
    -0.81
     continúas
    -0.81
    ).</
    -0.81
    FieldNumber
    -0.79
    nologue
    -0.79
    POSITIVE LOGITS
    “
    0.71
    (
    0.69
     abiti
    0.66
    <strong>
    0.62
     الحره
    0.62
    <b>
    0.58
    "
    0.58
     pantaloni
    0.58
     felicità
    0.56
     provavelmente
    0.56
    Act Density 0.032%

    No Known Activations