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

    Neuronpedia

    INDEX
    Explanations

    the word "of" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.05
    4:0.05
    5:0.02
    6:0.10
    7:0.15
    8:0.04
    9:0.03
    10:0.10
    11:0.31
    Negative Logits
    population
    -2.07
     Eag
    -1.78
    ilee
    -1.72
     Ethnic
    -1.65
    veyard
    -1.62
     Grey
    -1.59
    cliffe
    -1.59
    employment
    -1.56
    outh
    -1.56
    pop
    -1.55
    POSITIVE LOGITS
     concess
    2.13
    ertodd
    2.02
     incomp
    1.75
     diagrams
    1.69
     caveats
    1.69
     pci
    1.67
     inval
    1.65
     propell
    1.64
     fung
    1.64
     cartridges
    1.62
    Act Density 0.001%

    No Known Activations