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

    Neuronpedia

    INDEX
    Explanations

    the word "even" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.12
    3:0.05
    4:0.06
    5:0.05
    6:0.12
    7:0.04
    8:0.08
    9:0.05
    10:0.09
    11:0.23
    Negative Logits
    kefeller
    -1.73
    版
    -1.70
    aughtered
    -1.69
    aques
    -1.66
    saf
    -1.59
     Mehran
    -1.57
    Fight
    -1.52
    Truth
    -1.52
     Donation
    -1.50
     Pastebin
    -1.47
    POSITIVE LOGITS
     portfolios
    1.46
     contracting
    1.45
    acting
    1.44
     agent
    1.43
     Barney
    1.42
     サーティワン
    1.40
     Sed
    1.40
     estates
    1.35
     Daniels
    1.35
     divor
    1.34
    Act Density 0.023%

    No Known Activations