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

    Neuronpedia

    INDEX
    Explanations

    financial cost-related terms and figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ende
    -0.75
    aucas
    -0.74
    ixture
    -0.74
    xual
    -0.73
    TextColor
    -0.70
    soType
    -0.70
    ESE
    -0.70
    apons
    -0.68
    ARDS
    -0.65
    icip
    -0.64
    POSITIVE LOGITS
     upkeep
    1.00
     cents
    0.92
    -$
    0.91
     incurred
    0.91
     taxpayers
    0.90
    USD
    0.88
     upfront
    0.88
     prohib
    0.87
     billions
    0.86
    £
    0.86
    Act Density 0.138%

    No Known Activations