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

    Neuronpedia

    INDEX
    Explanations

    arguments or discussions related to specific topics, like church, law, names, and terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mp
    -0.61
    BuyableInstoreAndOnline
    -0.59
    udo
    -0.56
    cour
    -0.56
    ahan
    -0.55
    odder
    -0.54
    roxy
    -0.54
     Yel
    -0.53
     phased
    -0.53
     roundup
    -0.51
    POSITIVE LOGITS
     differently
    0.90
     intimately
    0.86
     beforehand
    0.85
     firsthand
    0.81
     correctly
    0.80
     existed
    0.79
    worthiness
    0.78
     accurately
    0.77
     exists
    0.76
    vantage
    0.75
    Act Density 0.459%

    No Known Activations