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

    Neuronpedia

    INDEX
    Explanations

    references to large quantities of physical items, specifically 'tons'

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measures of weight, specifically in tons or tonnes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.70
     resemb
    -0.67
    hall
    -0.67
    Dub
    -0.66
    Loop
    -0.63
    cards
    -0.63
    Journal
    -0.63
    WHERE
    -0.62
    govern
    -0.62
     Advice
    -0.62
    POSITIVE LOGITS
     lbs
    1.01
     tonnes
    0.97
     barrels
    0.94
     pounds
    0.93
    poons
    0.91
     tons
    0.86
     apiece
    0.82
    atsu
    0.77
    iles
    0.74
     gallons
    0.74
    Act Density 0.016%

    No Known Activations