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

    Neuronpedia

    INDEX
    Explanations

    terms related to competition or competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMI
    -0.77
    stones
    -0.76
    ################
    -0.75
    DonaldTrump
    -0.73
    FORE
    -0.72
    gur
    -0.70
    olen
    -0.69
    ocrates
    -0.69
    slave
    -0.67
    ĸļ
    -0.66
    POSITIVE LOGITS
     advantages
    0.98
     minded
    0.97
    ly
    0.96
     advantage
    0.95
     multiplayer
    0.88
     disadvantage
    0.86
     Advantage
    0.85
     edge
    0.83
     juices
    0.83
     streak
    0.82
    Act Density 0.008%

    No Known Activations