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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the value or cost of items

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Puzz
    -0.78
     Ern
    -0.77
    PDATE
    -0.66
     Kub
    -0.64
     Edison
    -0.62
     Ribbon
    -0.61
    æĸ
    -0.59
     Townsend
    -0.58
     Gaw
    -0.58
     Koz
    -0.58
    POSITIVE LOGITS
    umes
    0.97
    ume
    0.87
    iness
    0.86
    umed
    0.81
    folios
    0.80
     trillions
    0.77
    ongs
    0.77
    worth
    0.76
    ily
    0.74
    uming
    0.72
    Act Density 0.038%

    No Known Activations