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

    Neuronpedia

    INDEX
    Explanations

    mentions of monetary amounts in dollars

    oai_token-act-pair · gpt-3.5-turbo

    references to large amounts of money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.68
    eways
    -0.67
    eor
    -0.66
    ivity
    -0.65
    âĹ¼
    -0.64
     Blaz
    -0.64
     Silent
    -0.64
    Urban
    -0.64
    Ble
    -0.64
    sole
    -0.63
    POSITIVE LOGITS
     dollars
    1.33
     dollar
    0.95
    dollar
    0.91
     Dollars
    0.89
     sterling
    0.85
     ($
    0.85
     worth
    0.80
     USD
    0.78
     ($)
    0.77
    hyde
    0.77
    Act Density 0.012%

    No Known Activations