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

    Neuronpedia

    INDEX
    Explanations

    references to gaming mechanics or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оки
    -0.15
     Jer
    -0.14
    hong
    -0.14
    refund
    -0.14
     PI
    -0.14
     Sno
    -0.14
     Reb
    -0.14
    stan
    -0.13
     Bend
    -0.13
     Carey
    -0.13
    POSITIVE LOGITS
     card
    0.31
     cards
    0.29
    deck
    0.27
     deck
    0.27
     Cards
    0.25
    Deck
    0.25
     Deck
    0.24
    Cards
    0.23
     Card
    0.23
     decks
    0.23
    Act Density 0.005%

    No Known Activations