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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.02
     kasarigan
    -0.90
    IFORN
    -0.74
    ########.
    -0.73
     Anſ
    -0.71
     Soph
    -0.68
     ſever
    -0.67
     Transc
    -0.66
    PMailer
    -0.65
    تقاوى
    -0.64
    POSITIVE LOGITS
     متعلقه
    0.66
     strijd
    0.58
    <bos>
    0.58
     Juifs
    0.55
    ↵
    0.54
     peines
    0.51
     informací
    0.51
    </td>
    0.51
     legyen
    0.50
    </h4>
    0.50
    Act Density 0.036%

    No Known Activations