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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" and potentially identify structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥ŀ
    -0.86
    ruciating
    -0.76
    ishers
    -0.71
    è¦ļéĨĴ
    -0.69
     thumbnail
    -0.66
    ished
    -0.65
    ¥µ
    -0.64
     entrances
    -0.62
     oats
    -0.61
    osponsors
    -0.61
    POSITIVE LOGITS
    abeth
    1.28
    peed
    1.13
    aurus
    1.05
    earch
    1.03
    olation
    0.94
    olate
    0.92
    terness
    0.92
    ciplinary
    0.92
    pora
    0.91
    rael
    0.91
    Act Density 0.048%

    No Known Activations