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

    Neuronpedia

    INDEX
    Explanations

    measurements of weight in kilograms

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to weight in kilograms and pounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.79
    bidden
    -0.69
    structed
    -0.67
    GROUND
    -0.67
    BOOK
    -0.63
     Explain
    -0.62
    cknowled
    -0.61
    displayText
    -0.60
    vironment
    -0.60
     Byz
    -0.59
    POSITIVE LOGITS
    atsu
    0.95
     gorilla
    0.88
    kg
    0.85
     lbs
    0.83
    ross
    0.82
     kg
    0.79
    rafted
    0.78
    lbs
    0.77
     kilograms
    0.76
    ingly
    0.75
    Act Density 0.021%

    No Known Activations