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

    Neuronpedia

    INDEX
    Explanations

    references to financial transactions and financing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.07
    4:0.13
    5:0.02
    6:0.04
    7:0.38
    8:0.03
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
    izens
    -1.64
    anon
    -1.61
    undy
    -1.52
    famous
    -1.51
    mbuds
    -1.51
    bryce
    -1.48
    erential
    -1.45
    estyles
    -1.45
    omsky
    -1.44
    emale
    -1.42
    POSITIVE LOGITS
     salvation
    1.75
     futures
    1.56
     initiation
    1.51
     impending
    1.46
     costs
    1.42
     costly
    1.42
     sails
    1.42
     subscription
    1.41
     victory
    1.36
     undertaking
    1.36
    Act Density 0.001%

    No Known Activations