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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "For" indicating examples or illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.71
    marine
    -0.66
    arest
    -0.64
    zona
    -0.61
    Introduced
    -0.60
    æĺ¯
    -0.58
    smanship
    -0.58
    itiz
    -0.56
    BP
    -0.56
    ucl
    -0.55
    POSITIVE LOGITS
    gotten
    1.34
    cing
    1.32
     example
    1.27
    bidden
    1.25
     instance
    1.20
    ced
    1.14
     starters
    1.08
    give
    1.06
    getting
    0.94
     comparison
    0.92
    Act Density 0.071%

    No Known Activations