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

    Neuronpedia

    INDEX
    Explanations

    punctuation, primarily quotation marks and commas, indicating dialogue or cited phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ais
    -0.64
    RIEL
    -0.63
     Infin
    -0.63
     bờ
    -0.63
     Ker
    -0.61
     Berthe
    -0.60
    chaik
    -0.59
    <![
    -0.59
     rest
    -0.59
     Mait
    -0.59
    POSITIVE LOGITS
    ,"
    1.66
    ."
    1.64
    ?"
    1.56
    ,”
    1.55
    .”
    1.51
    )."
    1.51
    ?”
    1.47
    .’”
    1.42
    ).”
    1.41
    .'"
    1.40
    Act Density 0.189%

    No Known Activations