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

    Neuronpedia

    INDEX
    Explanations

    mentions of high costs or expenses

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eming
    -0.75
    aucas
    -0.71
    zona
    -0.71
    apons
    -0.68
    à¼
    -0.63
    ocent
    -0.63
    ndra
    -0.62
    owship
    -0.62
    iphany
    -0.61
    ipation
    -0.61
    POSITIVE LOGITS
     dollars
    1.01
     dearly
    0.97
     taxpayers
    0.96
    -$
    0.95
     apiece
    0.91
     upfront
    0.90
     ($
    0.89
     (£
    0.88
    $$
    0.87
     USD
    0.86
    Act Density 0.145%

    No Known Activations