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

    Neuronpedia

    INDEX
    Explanations

    numbers and hyphenated ranges

    oai_token-act-pair · gpt-3.5-turbo

    quantities expressed as fractions or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.65
    upon
    -0.65
    76561
    -0.64
    angan
    -0.63
    ↵Âł
    -0.63
    rade
    -0.62
    ffen
    -0.62
    Fal
    -0.62
    Helper
    -0.61
    prototype
    -0.60
    POSITIVE LOGITS
     dozen
    1.41
     hundred
    1.30
    dozen
    1.19
     thousand
    1.14
     thirds
    1.12
     lakh
    1.07
    thirds
    1.00
     million
    0.99
     Hundred
    0.94
     MILL
    0.86
    Act Density 0.120%

    No Known Activations