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

    Neuronpedia

    INDEX
    Explanations

    words related to playing cards and card games

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of cards, particularly in gaming or transaction contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Progress
    -0.71
    ¿½
    -0.69
     Dak
    -0.67
     Osborne
    -0.66
     Amend
    -0.65
     Bradford
    -0.64
     LAT
    -0.63
     Kut
    -0.63
     Fiction
    -0.62
     Pok
    -0.61
    POSITIVE LOGITS
    Card
    1.11
    inals
    1.10
     card
    1.08
    holder
    1.06
    iologist
    1.05
     cards
    1.04
    card
    1.01
    holders
    0.96
    igans
    0.95
    cards
    0.93
    Act Density 0.017%

    No Known Activations