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

    Neuronpedia

    INDEX
    Explanations

    numbers representing large amounts

    oai_token-act-pair · gpt-3.5-turbo

    quantities related to large numbers in the context of organizations or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bidden
    -0.71
    gotten
    -0.70
    zyme
    -0.68
     heav
    -0.67
     tightening
    -0.66
    izons
    -0.63
    acht
    -0.62
    agraph
    -0.62
    changes
    -0.61
    butt
    -0.61
    POSITIVE LOGITS
    s
    1.37
     crore
    1.07
    sie
    1.05
     lakh
    0.98
    sv
    0.96
    alos
    0.94
    ertodd
    0.93
    istani
    0.92
    sg
    0.85
    sburgh
    0.85
    Act Density 0.013%

    No Known Activations