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

    Neuronpedia

    INDEX
    Explanations

    references to gaming or card playing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umi
    -0.16
    ç°
    -0.16
     Moody
    -0.15
    jac
    -0.15
     deposit
    -0.15
     Dialog
    -0.15
    istan
    -0.15
     consort
    -0.15
     Gent
    -0.15
     Brooks
    -0.14
    POSITIVE LOGITS
     decks
    0.29
     deck
    0.28
    deck
    0.25
    Constructed
    0.23
    Deck
    0.21
    .deck
    0.21
     Deck
    0.21
     card
    0.21
     decking
    0.20
     cards
    0.20
    Act Density 0.017%

    No Known Activations