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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or inevitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.17
    3:0.08
    4:0.03
    5:0.05
    6:0.11
    7:0.03
    8:0.05
    9:0.05
    10:0.05
    11:0.29
    Negative Logits
    FY
    -1.86
     Darling
    -1.74
     rehearsal
    -1.71
     schedules
    -1.70
     Studios
    -1.69
     pregnancies
    -1.68
     resolutions
    -1.65
     airs
    -1.62
     Abbott
    -1.61
     Cran
    -1.60
    POSITIVE LOGITS
    ibaba
    2.08
    gdala
    2.02
    alions
    1.77
    andise
    1.75
    atility
    1.75
    orsi
    1.74
    MpServer
    1.68
    folios
    1.66
    hemat
    1.65
    cipl
    1.61
    Act Density 0.006%

    No Known Activations