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

    Neuronpedia

    INDEX
    Explanations

    units of weight such as kilograms, tons, and litres

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and measurements of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.89
    cknow
    -0.75
     Doodle
    -0.69
    places
    -0.67
    learn
    -0.66
    Developer
    -0.65
    ĻĤ
    -0.65
     skelet
    -0.63
     Leigh
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     lbs
    1.06
    poons
    1.02
     bottles
    0.93
     helium
    0.92
     gorilla
    0.92
     apiece
    0.91
     ammonia
    0.87
     pounds
    0.87
     kilograms
    0.87
     tonnes
    0.85
    Act Density 0.072%

    No Known Activations