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

    Neuronpedia

    INDEX
    Explanations

    bold text formatting in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.06
     $_"
    -0.92
     
    -0.89
     ब्रेकडाउन
    -0.83
     الرياضيه
    -0.83
    felves
    -0.82
    \<^
    -0.82
    ---*/
    -0.81
     Theſe
    -0.80
    nefs
    -0.79
    POSITIVE LOGITS
    <b>
    3.03
    </b>
    1.76
    <i>
    1.53
    <strong>
    1.51
    <u>
    1.17
    </i>
    1.09
    dfrac
    1.05
    <em>
    0.93
    <blockquote>
    0.91
    mathbf
    0.90
    Act Density 0.069%

    No Known Activations