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

    Neuronpedia

    INDEX
    Explanations

    references to energy efficiency and environmental impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Fuel/energy efficiency

    np_acts-logits-general · gemini-2.0-flash

    energy efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AttributeSet
    -0.55
    ništvo
    -0.52
    RTGC
    -0.51
    tenis
    -0.51
    Soli
    -0.50
    Халык
    -0.49
     soutien
    -0.49
     Accessible
    -0.49
    RTLD
    -0.48
    IsMutable
    -0.48
    POSITIVE LOGITS
     efficiency
    1.80
     Efficiency
    1.55
    efficiency
    1.53
     efficient
    1.52
     efficiencies
    1.50
    Efficiency
    1.50
     EFFICIENCY
    1.39
     Efficient
    1.37
    efficient
    1.35
     efisien
    1.32
    Act Density 0.432%

    No Known Activations