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

    Neuronpedia

    INDEX
    Explanations

    references to international organizations and treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.43
    7:0.05
    8:0.03
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
     tw
    -1.48
    nen
    -1.43
     chewing
    -1.32
    wagen
    -1.32
     laz
    -1.29
     cakes
    -1.27
     toes
    -1.27
    jee
    -1.26
     cyl
    -1.25
    bye
    -1.23
    POSITIVE LOGITS
    スト
    1.67
    ワ
    1.50
    ミ
    1.47
    フォ
    1.42
    ATIONS
    1.42
    ourses
    1.38
    ARS
    1.36
    rencies
    1.34
    hemat
    1.31
     Incarn
    1.30
    Act Density 0.016%

    No Known Activations