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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "date."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.06
    4:0.09
    5:0.03
    6:0.09
    7:0.05
    8:0.04
    9:0.06
    10:0.09
    11:0.28
    Negative Logits
    ppa
    -1.71
    roy
    -1.70
     repositories
    -1.69
    links
    -1.57
    dates
    -1.57
    leigh
    -1.55
    seed
    -1.54
    ROM
    -1.54
     homebrew
    -1.50
    OST
    -1.50
    POSITIVE LOGITS
     Marketable
    2.08
     Cancel
    1.93
     ACTIONS
    1.72
    anship
    1.68
    endas
    1.65
     Mobility
    1.64
     Tradable
    1.61
    者
    1.60
    uyomi
    1.56
     Compensation
    1.55
    Act Density 0.002%

    No Known Activations