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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rankings or positions of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cast
    -0.48
    <bos>
    -0.48
    zelfde
    -0.47
     arada
    -0.45
     casting
    -0.44
     vecka
    -0.43
    rsiniz
    -0.43
     dore
    -0.42
    やってきた
    -0.42
     vindo
    -0.42
    POSITIVE LOGITS
     fastest
    0.98
     largest
    0.97
    ⓧ
    0.91
     widest
    0.91
     smartest
    0.90
     ویکی‌پدیا
    0.88
     brightest
    0.88
     greatest
    0.88
    #+#
    0.87
     busiest
    0.86
    Act Density 0.296%

    No Known Activations