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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strategic card games

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Þ
    -1.15
     certific
    -1.03
    ß
    -0.96
    LAB
    -0.92
     satell
    -0.91
     contrace
    -0.90
    ©¶æ
    -0.89
    yright
    -0.89
     IPM
    -0.89
     corrid
    -0.87
    POSITIVE LOGITS
    Blade
    1.28
    blade
    1.25
    Spell
    1.17
     Cloak
    1.17
     Colossus
    1.15
     Armor
    1.15
    Armor
    1.12
     Blade
    1.11
    Weapon
    1.10
     Plate
    1.09
    Act Density 1.386%

    No Known Activations