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
    1:0.10
    2:0.09
    3:0.07
    4:0.06
    5:0.09
    6:0.08
    7:0.07
    8:0.07
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    verett
    -2.68
    \<
    -2.59
     antitrust
    -2.56
    SpaceEngineers
    -2.46
     occupational
    -2.41
     spokes
    -2.41
     <[
    -2.37
     quit
    -2.33
     vectors
    -2.32
    quit
    -2.30
    POSITIVE LOGITS
     Yi
    2.62
     Haram
    2.58
     degraded
    2.53
    ulkan
    2.51
    blem
    2.45
     jewel
    2.44
     Gems
    2.42
     Kap
    2.33
     Ey
    2.27
    ESCO
    2.24
    Act Density 0.000%

    No Known Activations