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

    Neuronpedia

    INDEX
    Explanations

    mentions of bots, especially in the context of technology and online interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to bots and automated systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayed
    -0.75
    deen
    -0.74
    inness
    -0.74
    leased
    -0.73
     SD
    -0.72
    reflect
    -0.71
    ensation
    -0.69
     Fitzgerald
    -0.69
     Cheney
    -0.67
     Quart
    -0.67
    POSITIVE LOGITS
     bot
    4.01
     Bot
    2.81
    Bot
    2.59
     bots
    2.50
    bot
    2.30
     Bots
    1.84
    bots
    1.80
     robot
    1.29
     Robot
    1.04
     spam
    1.02
    Act Density 0.023%

    No Known Activations