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

    Neuronpedia

    INDEX
    Explanations

    HTML formatting elements, specifically emphasis tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MONT
    -0.81
     Wiesen
    -0.79
    GHIJKLM
    -0.75
    ^(@)
    -0.75
    leſs
    -0.73
     Whit
    -0.71
     CascadeType
    -0.69
    Laurie
    -0.69
    oudre
    -0.68
    entric
    -0.68
    POSITIVE LOGITS
    </em>
    2.90
    </i>
    2.19
    </u>
    1.74
    </code>
    1.68
    </strong>
    1.57
    </h6>
    1.53
    <em>
    1.51
    </s>
    1.45
    }*/
    1.35
    </sub>
    1.34
    Act Density 0.010%

    No Known Activations