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

    Neuronpedia

    INDEX
    Explanations

    specific words that repeat consistently in the text like "para" and "Ana" and possibly the function patterns that link them together within the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "para" and variations related to certain contexts or themes, particularly in titles or sections of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.87
    Ö¼
    -0.81
    esley
    -0.80
    ories
    -0.78
    sburg
    -0.76
    hardt
    -0.76
     Tycoon
    -0.72
    hart
    -0.70
    endor
    -0.70
    Reviewer
    -0.70
    POSITIVE LOGITS
     para
    0.98
     compr
    0.93
    forming
    0.82
    esthes
    0.80
     mosqu
    0.79
     tion
    0.78
     Karin
    0.76
     Suk
    0.76
    esthesia
    0.76
     pse
    0.75
    Act Density 0.009%

    No Known Activations