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

    Neuronpedia

    INDEX
    Explanations

    instances of quote or blockquote delimiters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     par
    -0.79
     ber
    -0.78
     le
    -0.73
     po
    -0.72
    :\/\/
    -0.71
     ri
    -0.70
     co
    -0.69
     Vogel
    -0.69
     dot
    -0.68
     met
    -0.68
    POSITIVE LOGITS
    <blockquote>
    1.58
     itſelf
    1.32
     Houſe
    1.18
    <h5>
    1.15
     ſhe
    1.13
     greateſt
    1.13
     myſelf
    1.13
     alſo
    1.13
    <h4>
    1.12
     Cæsar
    1.12
    Act Density 0.008%

    No Known Activations