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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.09
    4:0.07
    5:0.09
    6:0.07
    7:0.08
    8:0.09
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     Kyoto
    -2.90
     decipher
    -2.75
     kindred
    -2.61
     ancest
    -2.47
    document
    -2.46
     Scandinavian
    -2.46
     deline
    -2.45
     anthrop
    -2.45
     Yosemite
    -2.41
     Neurolog
    -2.40
    POSITIVE LOGITS
    elight
    3.07
    odder
    2.96
    VERTISEMENT
    2.89
    bek
    2.72
    zb
    2.64
    bh
    2.60
    rition
    2.58
    rophe
    2.57
    BS
    2.56
    eker
    2.52
    Act Density 0.000%

    No Known Activations