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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences and paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CFS
    -0.63
    !")
    -0.60
    )");
    -0.59
    AddTagHelper
    -0.58
    )++;
    -0.56
    </tfoot>
    -0.56
    webElementXpaths
    -0.55
     CFS
    -0.54
     Shakspeare
    -0.54
     itſelf
    -0.53
    POSITIVE LOGITS
     around
    0.92
     AROUND
    0.83
     Around
    0.80
    Around
    0.79
    around
    0.76
    tagHelperRunner
    0.73
     intorno
    0.69
    AROUND
    0.64
    клопе
    0.64
     autour
    0.64
    Act Density 0.057%

    No Known Activations