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

    Neuronpedia

    INDEX
    Explanations

    text related to categories

    oai_token-act-pair · gpt-3.5-turbo

    references to various categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.90
     Zimmer
    -0.79
     RIS
    -0.70
    kj
    -0.67
     Trojan
    -0.61
    gotten
    -0.61
     ultras
    -0.61
     Rez
    -0.59
     lifes
    -0.58
    ippi
    -0.57
    POSITIVE LOGITS
    naire
    0.92
    category
    0.86
     categories
    0.79
     guiActiveUnfocused
    0.79
    ifier
    0.78
    rss
    0.77
    oola
    0.76
     category
    0.76
    ãģĨ
    0.76
    Category
    0.75
    Act Density 0.016%

    No Known Activations