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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of liquid substances

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of liquids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.72
    addon
    -0.72
    reon
    -0.69
    ths
    -0.68
    saf
    -0.67
     accur
    -0.65
    oÄŁ
    -0.65
    shire
    -0.64
    roads
    -0.63
    ebook
    -0.62
    POSITIVE LOGITS
     nitrogen
    1.14
    ators
    1.03
    ation
    1.03
    ated
    0.95
    itate
    0.90
     cooled
    0.88
    ator
    0.85
    ating
    0.85
    ity
    0.83
     helium
    0.83
    Act Density 0.036%

    No Known Activations