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

    Neuronpedia

    INDEX
    Explanations

    mentions of coins and coin-related activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABE
    -0.75
    ————————
    -0.70
     Abdel
    -0.68
     Narr
    -0.65
     Brah
    -0.62
     Atmosp
    -0.61
     Damn
    -0.61
     Syl
    -0.61
     STATS
    -0.60
     Huge
    -0.60
    POSITIVE LOGITS
     purse
    0.94
    age
    0.93
     toss
    0.90
    join
    0.88
    coins
    0.87
    agement
    0.86
    ages
    0.86
    abul
    0.85
     coins
    0.85
    Desk
    0.85
    Act Density 0.017%

    No Known Activations