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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call for action or a breaking point

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the word "enough" and its variations, indicating a demand for change or realization of limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousands
    -0.87
    Ń·
    -0.86
    afort
    -0.83
    eer
    -0.77
    eston
    -0.76
    uay
    -0.75
    MA
    -0.65
    eson
    -0.65
    ighth
    -0.65
    ift
    -0.64
    POSITIVE LOGITS
     times
    0.79
    !?
    0.66
     episodes
    0.64
    times
    0.62
     negativity
    0.61
    ?!
    0.60
    inventoryQuantity
    0.59
    !?"
    0.59
     affairs
    0.58
     credit
    0.57
    Act Density 0.035%

    No Known Activations