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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial transactions and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.11
    2:0.04
    3:0.11
    4:0.07
    5:0.02
    6:0.06
    7:0.04
    8:0.08
    9:0.05
    10:0.09
    11:0.04
    Negative Logits
     swat
    -1.64
     nightmares
    -1.64
     supermarkets
    -1.61
     malls
    -1.57
    ��
    -1.56
     warehouses
    -1.56
     kitchens
    -1.55
    Arcade
    -1.52
    ragon
    -1.51
     studios
    -1.51
    POSITIVE LOGITS
    brance
    1.95
    uration
    1.94
     (%
    1.77
     designation
    1.69
     action
    1.59
     option
    1.59
     requirement
    1.56
     interaction
    1.55
     relationship
    1.53
    rection
    1.53
    Act Density 0.181%

    No Known Activations