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

    Neuronpedia

    INDEX
    Explanations

    references to card games and card-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.02
    lihood
    -1.01
    -1.00
    ."</
    -1.00
    InjectAttribute
    -0.99
    ]`
    -0.98
    "]];
    -0.97
    ,:);
    -0.96
    })]
    -0.94
    ,:]
    -0.94
    POSITIVE LOGITS
     cards
    1.91
     Cards
    1.87
     card
    1.71
     Card
    1.69
     CARD
    1.64
    Cards
    1.62
    Card
    1.61
    cards
    1.59
    CARD
    1.55
    card
    1.54
    Act Density 0.056%

    No Known Activations