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

    Neuronpedia

    INDEX
    Explanations

    mathematical fractions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виб
    -0.17
    èµ·æĿ¥
    -0.16
    ATIO
    -0.16
    Ñģлов
    -0.15
    å¤ļ
    -0.15
    ippo
    -0.14
    ONO
    -0.14
    printStats
    -0.14
    uld
    -0.14
    ppo
    -0.14
    POSITIVE LOGITS
    -than
    0.18
     than
    0.17
    Ñĥди
    0.15
     Jana
    0.15
    UA
    0.15
    Qualified
    0.14
    0.14
    rer
    0.14
    YM
    0.14
    ovny
    0.14
    Act Density 0.036%

    No Known Activations