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

    Neuronpedia

    INDEX
    Explanations

    HTML and formatting elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </b>
    -1.33
    </i>
    -1.22
     propOrder
    -1.08
     betweenstory
    -1.05
     Wikimedijinoj
    -1.02
     ModelExpression
    -0.98
     kasarigan
    -0.95
     <=",
    -0.94
     Arxivat
    -0.93
     '\\;'
    -0.93
    POSITIVE LOGITS
    <strong>
    2.47
    </strong>
    1.94
    </em>
    1.77
    <em>
    1.54
    َّ
    0.88
    ِّ
    0.77
     fi
    0.76
    fi
    0.71
    ُّ
    0.67
     — 
    0.62
    Act Density 0.146%

    No Known Activations