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

    Neuronpedia

    INDEX
    Explanations

    references to energy production sources and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.04
    4:0.09
    5:0.02
    6:0.04
    7:0.34
    8:0.03
    9:0.03
    10:0.20
    11:0.05
    Negative Logits
     nudity
    -2.03
     affili
    -1.94
    onym
    -1.91
     plagiar
    -1.91
     collaborators
    -1.76
     anatomical
    -1.74
     anonym
    -1.72
     hairst
    -1.67
     affiliation
    -1.65
    iasis
    -1.62
    POSITIVE LOGITS
     generators
    2.22
     electricity
    1.91
     pumps
    1.88
     watts
    1.87
     Watts
    1.82
     kW
    1.77
     generator
    1.75
     converter
    1.74
     turbines
    1.72
     amps
    1.68
    Act Density 0.013%

    No Known Activations