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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks and other forms of dialogue indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.92
     Monfieur
    -0.82
     ſmall
    -0.79
     Jefus
    -0.79
     Perſ
    -0.77
     Majefty
    -0.77
     houſe
    -0.74
     pleaſure
    -0.74
     Diſ
    -0.73
     Inſ
    -0.71
    POSITIVE LOGITS
     disambiguazione
    0.74
    <bos>
    0.65
    Geplaatst
    0.65
    webElementXpaths
    0.60
    Спасылкі
    0.60
    XmlAccessType
    0.60
    mergeFrom
    0.59
     Seeder
    0.58
    Välislingid
    0.57
    UnsafeEnabled
    0.57
    Act Density 0.162%

    No Known Activations