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

    Neuronpedia

    INDEX
    Explanations

    measurements related to weight or quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements in grams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    joined
    -0.77
    sole
    -0.76
    ARP
    -0.68
    Dub
    -0.67
    lined
    -0.65
    wards
    -0.65
     defe
    -0.64
    illance
    -0.63
     jan
    -0.62
     Keeper
    -0.61
    POSITIVE LOGITS
     grams
    1.28
    poons
    1.05
     kilograms
    0.87
     quantities
    0.85
     servings
    0.85
    cakes
    0.85
    Quantity
    0.85
    ertodd
    0.82
    matically
    0.80
    peed
    0.80
    Act Density 0.012%

    No Known Activations