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

    Neuronpedia

    INDEX
    Explanations

    textual elements that indicate notable beginnings or introductions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stuart
    -0.15
     пÑĢоÑĢ
    -0.14
    æľŁéĸĵ
    -0.14
    als
    -0.14
    ocale
    -0.14
    peri
    -0.13
    ines
    -0.13
     Administration
    -0.13
    abile
    -0.13
    á»Ĺ
    -0.13
    POSITIVE LOGITS
    intro
    0.16
    åĺĽ
    0.15
    Intro
    0.14
     introductory
    0.14
    lein
    0.14
     introducing
    0.14
    ommen
    0.14
    uum
    0.14
     giỼi
    0.14
     introdu
    0.14
    Act Density 0.059%

    No Known Activations