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

    Neuronpedia

    INDEX
    Explanations

    references to specific cards and strategies used in a competitive card game

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cn
    -0.43
     Cn
    -0.42
     censiti
    -0.42
    rungsseite
    -0.42
    OGND
    -0.41
    Datuak
    -0.41
    namentales
    -0.41
    GTCX
    -0.41
    phorbia
    -0.40
     Hale
    -0.40
    POSITIVE LOGITS
     deck
    1.49
     Deck
    1.44
    Deck
    1.37
    deck
    1.36
     decks
    1.36
     DECK
    1.26
     Decks
    1.24
    decks
    1.06
     decking
    0.87
    デッキ
    0.85
    Act Density 0.073%

    No Known Activations