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

    Neuronpedia

    INDEX
    Explanations

    file types, specifically image files in JPEG format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.51
     Embora
    -0.48
     first
    -0.48
     somewhat
    -0.46
     more
    -0.46
     confiança
    -0.45
     unicórnio
    -0.45
     rather
    -0.44
     most
    -0.43
     embora
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.90
    0.87
    NameInMap
    0.82
     surla
    0.78
    تقاوى
    0.75
    <unused14>
    0.75
    <unused28>
    0.75
    <pad>
    0.75
    出版年
    0.75
    [@BOS@]
    0.75
    Act Density 0.535%

    No Known Activations