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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating the context or framing of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.64
     frattempo
    -0.64
     gainera
    -0.62
    +#+#
    -0.56
    richTextPanel
    -0.54
     ویکی‌پدی
    -0.53
     архивлан
    -0.52
     للمعارف
    -0.52
     Paglinawan
    -0.52
    Климат
    -0.51
    POSITIVE LOGITS
     practice
    0.67
     relation
    0.66
     today
    0.64
     context
    0.61
     contexte
    0.61
     simplest
    0.60
    practice
    0.60
     simple
    0.59
     contemporary
    0.58
     our
    0.57
    Act Density 0.563%

    No Known Activations