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

    Neuronpedia

    INDEX
    Explanations

    information related to weights and measurements

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to weight and size measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    timeout
    -0.74
     backdoor
    -0.73
     hotline
    -0.73
    href
    -0.72
     Secondary
    -0.72
     loophole
    -0.67
     deepening
    -0.67
    venue
    -0.66
     pse
    -0.66
    atre
    -0.65
    POSITIVE LOGITS
     pounds
    1.49
     kilograms
    1.41
     lbs
    1.38
     kg
    1.32
    lbs
    1.30
     ounces
    1.23
     weighs
    1.18
     grams
    1.17
    kg
    1.16
     tonnes
    1.13
    Act Density 0.101%

    No Known Activations