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

    Neuronpedia

    INDEX
    Explanations

    financial figures and amounts

    oai_token-act-pair · gpt-3.5-turbo

    amounts of money or financial values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.75
    heter
    -0.71
    lev
    -0.65
     dissenting
    -0.64
     throats
    -0.63
    bye
    -0.60
    oko
    -0.60
    nu
    -0.59
     rhythms
    -0.58
    mony
    -0.57
    POSITIVE LOGITS
     USD
    0.91
     annually
    0.86
    -$
    0.81
     dollars
    0.80
     (£
    0.80
     Bonds
    0.80
    =$
    0.79
     bonds
    0.79
     ($
    0.78
     treasury
    0.77
    Act Density 0.318%

    No Known Activations