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

    Neuronpedia

    INDEX
    Explanations

    concepts related to cooperation and social behavior in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qli
    -0.16
    ÑĢаз
    -0.14
    zdy
    -0.14
    ضÙĬ
    -0.14
     poses
    -0.13
    _OT
    -0.13
    /DTD
    -0.13
    loth
    -0.13
    à¹Īว
    -0.13
    Gate
    -0.13
    POSITIVE LOGITS
     Nash
    0.30
     equilibrium
    0.28
     game
    0.27
     games
    0.25
     Prison
    0.24
    -game
    0.23
     Vick
    0.22
     welfare
    0.21
     Game
    0.20
     utility
    0.20
    Act Density 0.051%

    No Known Activations