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

    Neuronpedia

    INDEX
    Explanations

    nouns and adjectives related to descriptions and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     плоÑī
    -0.20
    \Collections
    -0.16
     práci
    -0.16
     пÑĢиÑģÑĤÑĥп
    -0.16
     ÑĢабоÑĤÑĭ
    -0.16
     дÑĢÑĥгой
    -0.15
    inda
    -0.15
     Compilation
    -0.15
     sposób
    -0.15
    ãģ²ãģ¨
    -0.15
    POSITIVE LOGITS
     вÑĢемÑı
    0.19
     знаÑĩение
    0.17
     ÑĤеÑĩение
    0.17
     лиÑĨо
    0.17
     полоÑĤ
    0.17
     колиÑĩе
    0.17
     покол
    0.17
     колиÑĩеÑģÑĤво
    0.17
     ÑģÑĢедÑģÑĤво
    0.16
     ÑĢаÑģÑĤение
    0.15
    Act Density 0.023%

    No Known Activations