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

    Neuronpedia

    INDEX
    Explanations

    numerical references or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilk
    -0.65
     Witten
    -0.65
     Horowitz
    -0.64
    (['/
    -0.64
     Scherer
    -0.63
     ban
    -0.61
    alities
    -0.61
     CascadeType
    -0.61
    grond
    -0.59
     Finney
    -0.59
    POSITIVE LOGITS
    </h6>
    1.82
    </h2>
    1.81
    </h3>
    1.80
    </h5>
    1.68
    </h4>
    1.68
    </h1>
    1.58
    </table>
    1.43
     Audiodateien
    1.33
    }}$\\
    1.31
    }}}}
    1.29
    Act Density 0.041%

    No Known Activations