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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to questioning authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.08
    5:0.09
    6:0.10
    7:0.07
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    \<
    -2.91
    ghazi
    -2.63
     裏�
    -2.55
     "$:/
    -2.54
    etheless
    -2.52
    >[
    -2.50
    GUI
    -2.45
     Oo
    -2.42
     incompetence
    -2.36
     mildly
    -2.31
    POSITIVE LOGITS
    ierce
    2.50
     Trader
    2.49
    unin
    2.44
     Naomi
    2.40
     Quantity
    2.36
    adish
    2.34
     Mutual
    2.31
    asin
    2.28
    tor
    2.26
    trade
    2.22
    Act Density 0.000%

    No Known Activations