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

    Neuronpedia

    INDEX
    Explanations

    the verb "been" in the passive voice context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.07
    7:0.08
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     rash
    -3.35
     sickness
    -3.22
     Rampage
    -3.15
     diarr
    -3.08
     vomiting
    -3.01
     Released
    -2.88
     contagious
    -2.74
     Muk
    -2.72
    2013
    -2.71
     kittens
    -2.68
    POSITIVE LOGITS
    hematic
    2.86
    dyl
    2.83
    raltar
    2.74
     Colt
    2.72
     Anglo
    2.71
    dB
    2.64
     Franco
    2.61
    fif
    2.61
     Chamberlain
    2.60
    DNA
    2.59
    Act Density 0.000%

    No Known Activations