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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.00
     وتسجيلات
    -0.97
     kasarigan
    -0.94
     ddelweddau
    -0.90
    mybatisplus
    -0.89
    protoimpl
    -0.89
     nahilalakip
    -0.87
     pinulongan
    -0.86
    Cyfeiriadau
    -0.86
    bootstrapcdn
    -0.86
    POSITIVE LOGITS
    “
    0.75
    I
    0.72
    It
    0.68
    As
    0.64
    That
    0.64
    .
    0.63
    The
    0.61
    We
    0.60
    And
    0.59
    Even
    0.58
    Act Density 0.046%

    No Known Activations