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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.06
    4:0.17
    5:0.03
    6:0.04
    7:0.17
    8:0.03
    9:0.02
    10:0.09
    11:0.21
    Negative Logits
    PLIED
    -1.48
    ursday
    -1.38
    bery
    -1.29
     invitation
    -1.26
     Skype
    -1.25
     skept
    -1.25
    agle
    -1.24
     IPM
    -1.23
     Kinect
    -1.21
    dding
    -1.20
    POSITIVE LOGITS
     Yards
    1.39
    andise
    1.34
     piles
    1.33
    isSpecialOrderable
    1.31
     towering
    1.31
     Rue
    1.23
    utenberg
    1.15
     Dek
    1.14
    aepernick
    1.13
     succession
    1.12
    Act Density 0.002%

    No Known Activations