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

    Neuronpedia

    INDEX
    Explanations

    instances of decisive actions or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.10
    11:0.09
    Negative Logits
    ima
    -1.67
    bh
    -1.64
    atan
    -1.62
    omorphic
    -1.59
    amphetamine
    -1.58
     rud
    -1.55
    irtual
    -1.55
    acons
    -1.51
     dest
    -1.51
    trak
    -1.51
    POSITIVE LOGITS
     beforehand
    1.69
    %]
    1.62
    hire
    1.62
     whiff
    1.54
     Jury
    1.44
     Trial
    1.44
     Prosecut
    1.43
     Spielberg
    1.42
     subpoena
    1.41
    successfully
    1.39
    Act Density 0.000%

    No Known Activations