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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating significance or prominence within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toff
    -0.48
    SharedCtor
    -0.47
    <eos>
    -0.46
     dore
    -0.46
     smtplib
    -0.46
     arada
    -0.45
    mtrl
    -0.44
    表
    -0.44
    isEnd
    -0.43
     casting
    -0.42
    POSITIVE LOGITS
     fastest
    0.96
     brightest
    0.88
     smartest
    0.87
     ویکی‌پدیا
    0.86
     cleanest
    0.86
     largest
    0.84
     strongest
    0.83
     slowest
    0.82
     highest
    0.80
     widest
    0.80
    Act Density 0.179%

    No Known Activations