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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags, specifically for emphasis elements like italics and strikethrough

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.91
     MONT
    -0.90
     Witten
    -0.85
     Wiesen
    -0.84
    leſs
    -0.82
    liothèque
    -0.82
    ificance
    -0.81
    windowFixed
    -0.81
    Laurie
    -0.81
    entric
    -0.81
    POSITIVE LOGITS
    </em>
    2.44
    </i>
    1.90
    </u>
    1.45
    </code>
    1.44
    <em>
    1.42
    </strong>
    1.36
    </h6>
    1.28
    </sub>
    1.21
    </s>
    1.20
    </sup>
    1.19
    Act Density 0.003%

    No Known Activations