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

    Neuronpedia

    INDEX
    Explanations

    references to financial figures and monetary amounts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.80
     orientation
    -0.75
     dialect
    -0.74
     polymorph
    -0.73
    heastern
    -0.72
     orient
    -0.72
    zona
    -0.71
     kissing
    -0.70
     contexts
    -0.70
    usalem
    -0.69
    POSITIVE LOGITS
     Costs
    1.25
     ($
    1.19
     Payments
    1.18
    -$
    1.16
     (£
    1.16
    ($
    1.12
     Pric
    1.12
     Prices
    1.11
    cash
    1.10
    Money
    1.09
    Act Density 0.344%

    No Known Activations