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 of weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.77
    GROUND
    -0.68
    bidden
    -0.66
     Explain
    -0.65
    ppelin
    -0.63
    vironment
    -0.62
    zig
    -0.62
    structed
    -0.61
    irie
    -0.61
     Lawn
    -0.60
    POSITIVE LOGITS
    atsu
    0.91
    kg
    0.85
     gorilla
    0.81
     kg
    0.79
     kilograms
    0.78
    ross
    0.77
     lbs
    0.77
    omez
    0.76
     ammonia
    0.74
    emouth
    0.74
    Act Density 0.012%

    No Known Activations