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

    Neuronpedia

    INDEX
    Explanations

    information related to published works, articles, and comments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of writing and publishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.66
     Nato
    -0.60
     decre
    -0.54
    amac
    -0.52
    ',"
    -0.51
    aceae
    -0.51
    eering
    -0.51
    estate
    -0.50
    aila
    -0.49
     disadvant
    -0.49
    POSITIVE LOGITS
     reader
    0.92
     archive
    0.86
    Reader
    0.85
     publication
    0.84
     editor
    0.83
     readers
    0.81
     blog
    0.80
     plagiar
    0.77
     Readers
    0.76
    archive
    0.76
    Act Density 1.948%

    No Known Activations