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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    key attributes or characteristics related to individuals and their qualifications or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatus
    -0.93
    Attempt
    -0.69
    OTUS
    -0.68
    cember
    -0.68
    agram
    -0.67
     Worse
    -0.66
    mine
    -0.65
    idden
    -0.65
    enum
    -0.65
    aughtered
    -0.64
    POSITIVE LOGITS
     versatility
    1.79
     simplicity
    1.56
     elegance
    1.49
     uniqueness
    1.48
     flexibility
    1.48
     richness
    1.47
     brilliance
    1.33
     sophistication
    1.31
     qualities
    1.31
     creativity
    1.31
    Act Density 1.195%

    No Known Activations