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

    Neuronpedia

    INDEX
    Explanations

    HTML or markup elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MONT
    -0.89
    Laurie
    -0.83
     Wiesen
    -0.83
    entric
    -0.81
     Witten
    -0.81
     Monfieur
    -0.79
    leſs
    -0.79
    windowFixed
    -0.78
     YB
    -0.77
     Houſe
    -0.77
    POSITIVE LOGITS
    </em>
    2.35
    </i>
    1.81
    <em>
    1.42
    </code>
    1.34
    </u>
    1.31
    </h6>
    1.25
    </strong>
    1.23
    </s>
    1.15
    </sub>
    1.13
    </sup>
    1.08
    Act Density 0.001%

    No Known Activations