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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to playing card games, specifically ones involving strategy and deck building

    oai_token-act-pair · gpt-3.5-turbo

    references to specific games and their mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supervised
    -0.77
    OPLE
    -0.76
     sitcom
    -0.75
     DAV
    -0.74
    çĶ°
    -0.73
     certific
    -0.73
     behavi
    -0.72
     UNCLASSIFIED
    -0.72
     proble
    -0.72
     professionally
    -0.72
    POSITIVE LOGITS
    Blade
    1.13
    romancer
    1.12
     Enchant
    1.10
    flame
    1.08
    blade
    1.07
    Spell
    1.07
    Sword
    1.04
     Primordial
    1.02
    steel
    1.01
     Cloak
    1.01
    Act Density 0.180%

    No Known Activations