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

    Neuronpedia

    INDEX
    Explanations

    words related to categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.25
    3:0.05
    4:0.06
    5:0.04
    6:0.08
    7:0.06
    8:0.04
    9:0.05
    10:0.23
    11:0.05
    Negative Logits
     profitable
    -1.90
     Profit
    -1.89
     wiser
    -1.73
     dependent
    -1.72
     Pyr
    -1.68
     Completed
    -1.66
     richer
    -1.66
     Investments
    -1.66
     financially
    -1.63
     administr
    -1.62
    POSITIVE LOGITS
    iage
    2.01
    psc
    1.87
     shaved
    1.83
    iple
    1.80
    shown
    1.78
    frequency
    1.75
    ricanes
    1.73
    fur
    1.71
    Mouse
    1.71
    brush
    1.70
    Act Density 0.001%

    No Known Activations