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

    Neuronpedia

    INDEX
    Explanations

    large numerical quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.68
    itiz
    -0.67
    krit
    -0.66
     envy
    -0.65
    venge
    -0.63
    imen
    -0.62
    abus
    -0.61
     Balk
    -0.60
    ufact
    -0.60
    ulture
    -0.60
    POSITIVE LOGITS
     hectares
    1.12
     acres
    1.10
     lbs
    1.10
     sq
    1.08
     pounds
    1.08
    lb
    1.05
     gallons
    1.02
     miles
    1.02
     tonnes
    1.01
    lbs
    1.01
    Act Density 0.550%

    No Known Activations