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

    Neuronpedia

    INDEX
    Explanations

    references to large amounts of money being spent

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and spending-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ells
    -0.71
     shores
    -0.69
    oor
    -0.66
    redd
    -0.66
     departures
    -0.62
    edom
    -0.61
    PH
    -0.61
     emergence
    -0.61
    itta
    -0.58
    sup
    -0.58
    POSITIVE LOGITS
     wisely
    1.05
     bucks
    0.87
     frivol
    0.86
     dollars
    0.85
     incarcer
    0.83
     efficiently
    0.81
     unnecessarily
    0.77
     taxpayer
    0.75
    ocating
    0.72
     (£
    0.71
    Act Density 0.110%

    No Known Activations