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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </i>
    -0.82
    </code>
    -0.74
    </b>
    -0.63
    cvtColor
    -0.59
    "
    -0.59
    ”
    -0.58
    "}
    -0.57
    </sup>
    -0.57
     BorderRadius
    -0.56
     (...)
    -0.55
    POSITIVE LOGITS
    Portály
    0.94
     propOrder
    0.94
    AccessorTable
    0.92
     Efq
    0.91
     autorytatywna
    0.91
     ostavi
    0.90
    InjectAttribute
    0.89
     للاسماء
    0.86
    :✨
    0.83
     chofe
    0.82
    Act Density 0.679%

    No Known Activations