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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and references to their actions or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.12
    4:0.37
    5:0.03
    6:0.04
    7:0.08
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    ivable
    -1.69
    Exit
    -1.60
     obser
    -1.59
     rinse
    -1.52
     ceremon
    -1.48
    xit
    -1.46
    lled
    -1.45
     ponder
    -1.45
     prest
    -1.41
    utterstock
    -1.38
    POSITIVE LOGITS
     actionGroup
    1.94
    bryce
    1.85
    omever
    1.77
    intosh
    1.74
     tastes
    1.70
    ector
    1.62
    soType
    1.52
    ECA
    1.49
    ozo
    1.46
    �
    1.45
    Act Density 0.018%

    No Known Activations