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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or groups being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.08
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    issions
    -1.99
    ission
    -1.90
    affiliated
    -1.74
    motion
    -1.69
     裏覚醒
    -1.66
    és
    -1.66
     withd
    -1.66
    icked
    -1.65
    raq
    -1.63
    opes
    -1.63
    POSITIVE LOGITS
     gigs
    1.70
     Restaur
    1.68
     Able
    1.63
     passers
    1.61
     Drill
    1.61
     handy
    1.58
    DERR
    1.55
     bragging
    1.52
     Mechdragon
    1.52
     Hungry
    1.51
    Act Density 0.000%

    No Known Activations