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

    Neuronpedia

    INDEX
    Explanations

    large numbers or quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Played
    -0.73
     holder
    -0.67
     creator
    -0.67
     landlord
    -0.66
    estine
    -0.66
     birthplace
    -0.65
     operator
    -0.65
    akery
    -0.64
    agame
    -0.63
    Politics
    -0.63
    POSITIVE LOGITS
     ounces
    1.22
     gallons
    1.20
     kilograms
    1.20
     pounds
    1.19
     copies
    1.15
     lbs
    1.09
     grams
    1.08
    lbs
    1.06
     tonnes
    1.03
     litres
    1.02
    Act Density 0.253%

    No Known Activations