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

    Neuronpedia

    INDEX
    Explanations

    references to healthcare policies and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.11
    2:0.12
    3:0.04
    4:0.06
    5:0.09
    6:0.11
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
    ealous
    -1.45
    astical
    -1.40
    mbuds
    -1.29
    bda
    -1.28
    heimer
    -1.24
    etheless
    -1.24
    pard
    -1.22
    umers
    -1.19
    ducers
    -1.19
    artney
    -1.19
    POSITIVE LOGITS
     �
    1.29
    ビ
    1.15
     裏�
    1.13
    BuyableInstoreAndOnline
    1.10
     etc
    1.05
    ヘ
    1.00
     max
    1.00
     sleeps
    0.99
     Nanto
    0.98
    "}],"
    0.98
    Act Density 1.290%

    No Known Activations