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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions in technical content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     propOrder
    -0.56
    RegressionTest
    -0.54
    uttered
    -0.49
     кор
    -0.47
    PyExc
    -0.44
    aneous
    -0.43
    :✨
    -0.42
    steamcommunity
    -0.42
     radic
    -0.42
    bustion
    -0.42
    POSITIVE LOGITS
     estekak
    0.66
    makeText
    0.65
     speranza
    0.65
     оригіналу
    0.62
     Exactos
    0.61
    ďaka
    0.60
    SBATCH
    0.60
     ویکی‌پدیای
    0.59
    SerializeField
    0.58
     nôtre
    0.58
    Act Density 0.110%

    No Known Activations