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

    Neuronpedia

    INDEX
    Explanations

    references to money

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICLE
    -0.75
    spect
    -0.69
    Minor
    -0.65
    Hug
    -0.65
     Hug
    -0.65
     Fuk
    -0.63
     Halls
    -0.63
     Klu
    -0.63
     Frem
    -0.63
     Ku
    -0.61
    POSITIVE LOGITS
     laundering
    1.42
    bags
    1.03
    dollar
    0.99
     ($
    0.97
     invested
    0.92
    aundering
    0.89
     ($)
    0.89
     spent
    0.87
    money
    0.87
    flow
    0.85
    Act Density 0.529%

    No Known Activations