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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "one of" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    phrases that repeatedly reference "one of" followed by a list or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.67
    urated
    -0.67
    rina
    -0.66
     ende
    -0.66
     surpr
    -0.63
    culosis
    -0.63
    chart
    -0.61
     condem
    -0.61
    allery
    -0.60
    ĸļ
    -0.60
    POSITIVE LOGITS
    ses
    0.78
     them
    0.77
     theirs
    0.76
    icial
    0.70
    course
    0.67
     course
    0.64
    them
    0.64
     whom
    0.62
     THEM
    0.62
     us
    0.62
    Act Density 0.102%

    No Known Activations