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

    Neuronpedia

    INDEX
    Explanations

    phrases related to energy infrastructure and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.18
    1:0.02
    2:0.11
    3:0.07
    4:0.04
    5:0.08
    6:0.18
    7:0.03
    8:0.08
    9:0.10
    10:0.02
    11:0.03
    Negative Logits
     Stout
    -3.54
     Scotch
    -3.50
     Skull
    -3.43
     Jackie
    -3.38
     ABV
    -3.29
     Malone
    -3.28
     Smoking
    -3.27
     Bigfoot
    -3.26
     Cultural
    -3.23
     Ven
    -3.15
    POSITIVE LOGITS
    Grid
    8.23
     grid
    7.94
    grid
    7.66
     Grid
    7.17
     grids
    7.14
    Tile
    3.93
    cells
    3.89
    column
    3.88
     arrays
    3.66
    gran
    3.66
    Act Density 0.010%

    No Known Activations