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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or legislative actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.15
    3:0.14
    4:0.10
    5:0.02
    6:0.03
    7:0.26
    8:0.04
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
     attm
    -1.58
    staking
    -1.53
    bucks
    -1.49
     unparalleled
    -1.46
     srfAttach
    -1.44
    !/
    -1.43
    ы
    -1.42
     depends
    -1.41
     reminds
    -1.40
     unforgettable
    -1.39
    POSITIVE LOGITS
     anymore
    1.89
     coerc
    1.75
     nor
    1.62
     improperly
    1.56
     indemn
    1.55
     NEC
    1.48
     complain
    1.42
     frivol
    1.42
     CoC
    1.41
     QC
    1.40
    Act Density 0.053%

    No Known Activations