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

    Neuronpedia

    INDEX
    Explanations

    references to cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.08
    3:0.09
    4:0.09
    5:0.07
    6:0.09
    7:0.08
    8:0.07
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     Alto
    -2.93
     Spike
    -2.90
     Boulder
    -2.85
     Whedon
    -2.79
     Burn
    -2.78
     Slayer
    -2.77
     Buffy
    -2.75
     Cast
    -2.69
     Willow
    -2.69
     Tara
    -2.66
    POSITIVE LOGITS
    ossier
    2.79
    龍�
    2.69
    illus
    2.58
     lobbying
    2.55
    ricanes
    2.52
     promul
    2.45
     exhibitions
    2.43
    ategories
    2.41
     hors
    2.33
     monarchy
    2.31
    Act Density 0.000%

    No Known Activations