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

    Neuronpedia

    INDEX
    Explanations

    actions and reactions in a video game context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.86
     Architects
    -0.82
    ropolitan
    -0.81
     Ethics
    -0.81
    saf
    -0.79
    esan
    -0.79
    arenthood
    -0.79
     responsibly
    -0.78
     holdings
    -0.77
    winner
    -0.76
    POSITIVE LOGITS
     buzzing
    1.25
     uncontroll
    1.24
     audible
    1.24
     vibration
    1.22
     bursts
    1.22
     coughing
    1.20
     flashes
    1.19
     noises
    1.17
     vibrations
    1.13
     sensations
    1.13
    Act Density 2.608%

    No Known Activations