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

    Neuronpedia

    INDEX
    Explanations

    HTML or CSS class names and elements within a web document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.31
     fi
    -1.09
     first
    -1.04
     fl
    -1.02
    fl
    -0.91
    </strong>
    -0.89
    fi
    -0.84
    </em>
    -0.83
     — 
    -0.81
    **/
    -0.78
    POSITIVE LOGITS
    <b>
    2.80
    </b>
    2.24
    </i>
    2.00
    <i>
    1.63
    dfrac
    1.52
     ${\
    0.95
    </td>
    0.88
    例文帳に追加
    0.78
    0.76
    0.76
    Act Density 0.135%

    No Known Activations