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

    Neuronpedia

    INDEX
    Explanations

    names or mentions of a specific individual, potentially a public figure

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names or titles followed by variations of 'Pr' indicating a connection to individuals, particularly in a formal or official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.72
     seiz
    -0.67
    aston
    -0.62
     Wonderland
    -0.62
    romeda
    -0.61
    DIR
    -0.61
    ¥µ
    -0.59
     Monroe
    -0.58
     Arri
    -0.57
     disadvant
    -0.57
    POSITIVE LOGITS
    ciples
    1.10
    cipled
    1.03
    itte
    0.86
    cess
    0.81
    xus
    0.75
    bably
    0.71
     mend
    0.70
    aceutical
    0.69
    fecture
    0.69
    achine
    0.67
    Act Density 0.053%

    No Known Activations