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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers or specifications in a dataset or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.59
    +#+#
    -0.56
    -0.51
     الرياضيه
    -0.50
    GraphicsUnit
    -0.50
    原始内容存档于
    -0.48
    DoubleQuotes
    -0.46
    InstrumentedTest
    -0.45
     Мексичка
    -0.44
    astéro
    -0.44
    POSITIVE LOGITS
    obre
    0.59
     ALF
    0.52
    kir
    0.52
    Gle
    0.51
     PAV
    0.50
    abl
    0.50
     Tanger
    0.48
     Trick
    0.47
     свер
    0.47
    leng
    0.47
    Act Density 0.584%

    No Known Activations