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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy efficiency and performance metrics in mechanical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irth
    -0.18
     edition
    -0.15
    byt
    -0.14
     transporter
    -0.14
     twice
    -0.14
     double
    -0.13
     universal
    -0.13
    alley
    -0.13
    universal
    -0.13
     diner
    -0.13
    POSITIVE LOGITS
     operating
    0.20
     duty
    0.20
    Operating
    0.19
     Operating
    0.18
     idle
    0.18
    -oper
    0.18
    .oper
    0.18
     loads
    0.18
     startup
    0.17
    -load
    0.17
    Act Density 0.085%

    No Known Activations