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

    Neuronpedia

    INDEX
    Explanations

    terms related to card games and deck building

    oai_token-act-pair · gpt-3.5-turbo

    references to decks in card games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.74
    çīĪ
    -0.73
    heric
    -0.73
    DonaldTrump
    -0.72
     antid
    -0.68
    ipient
    -0.65
    interstitial
    -0.61
     satellites
    -0.60
     cessation
    -0.59
     rings
    -0.59
    POSITIVE LOGITS
    lists
    1.46
    builder
    1.15
    list
    1.14
    igans
    1.06
    mates
    1.02
    nut
    1.01
    wright
    1.00
    building
    0.98
    yard
    0.97
    builders
    0.96
    Act Density 0.026%

    No Known Activations