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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.09
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     Puzzles
    -2.88
    20439
    -2.87
    NASA
    -2.86
     Ceres
    -2.72
     Ships
    -2.71
    items
    -2.70
    linux
    -2.65
    ICE
    -2.64
    erning
    -2.63
    WASHINGTON
    -2.62
    POSITIVE LOGITS
     endemic
    2.98
     Patriot
    2.64
     savage
    2.61
     appell
    2.60
     apartheid
    2.50
     sectarian
    2.48
     demonstr
    2.47
     incap
    2.45
    hetto
    2.43
     Serbian
    2.41
    Act Density 0.000%

    No Known Activations