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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to quantities or prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.02
    2:0.03
    3:0.10
    4:0.13
    5:0.04
    6:0.07
    7:0.05
    8:0.16
    9:0.10
    10:0.02
    11:0.07
    Negative Logits
     acknowledgment
    -1.87
     overs
    -1.68
     acknowledgement
    -1.66
     acknowled
    -1.59
     convictions
    -1.59
     appreci
    -1.54
    Acknowled
    -1.51
    gments
    -1.49
     metaphors
    -1.47
     conclusions
    -1.47
    POSITIVE LOGITS
    lished
    1.86
    sed
    1.72
    prev
    1.69
    oso
    1.67
    today
    1.62
     Shutterstock
    1.59
    steam
    1.57
     Frenchman
    1.57
     Nasa
    1.57
    ester
    1.56
    Act Density 0.000%

    No Known Activations