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

    Neuronpedia

    INDEX
    Explanations

    phrases related to energy conservation and efficiency

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gradual processes and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appell
    -0.71
    National
    -0.69
     publicly
    -0.65
     Kahn
    -0.65
     Luxem
    -0.65
     Jur
    -0.65
     openly
    -0.65
    ylum
    -0.63
     representatives
    -0.62
    Government
    -0.62
    POSITIVE LOGITS
     cooldown
    1.01
     cpu
    1.00
     reload
    0.94
     humidity
    0.91
     drying
    0.90
     downtime
    0.89
     timer
    0.88
     refill
    0.87
     airflow
    0.84
     cleanup
    0.83
    Act Density 0.903%

    No Known Activations