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

    Neuronpedia

    INDEX
    Explanations

    sections of code related to function definitions and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.72
    Pyx
    -0.70
    opoulos
    -0.69
     Gey
    -0.68
     onAnimation
    -0.66
     $("#
    -0.64
     Wikimedijinoj
    -0.64
     ModelRenderer
    -0.64
     Италијани
    -0.64
     Zong
    -0.64
    POSITIVE LOGITS
    </th>
    1.02
    </
    0.99
    ">)</
    0.96
    ."</
    0.95
     }}$}
    0.94
    </tr>
    0.91
    ↵
    0.90
    </caption>
    0.90
    %</
    0.86
    )</
    0.85
    Act Density 0.041%

    No Known Activations