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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy, heat, and efficiency in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.38
    7:0.03
    8:0.04
    9:0.04
    10:0.14
    11:0.08
    Negative Logits
    actionDate
    -1.82
    �
    -1.56
    生
    -1.45
     Maz
    -1.35
    AAA
    -1.35
    イト
    -1.34
    ADA
    -1.27
     Username
    -1.25
    )=(
    -1.24
    ーン
    -1.23
    POSITIVE LOGITS
    itiveness
    1.75
    ilation
    1.44
    multipl
    1.38
    chedel
    1.36
    ————
    1.35
    condition
    1.26
     Furious
    1.25
    ersive
    1.25
     condensed
    1.24
     engulf
    1.23
    Act Density 0.009%

    No Known Activations