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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks in legal or formal texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.86
    脚注の使い方
    -0.79
    ByExample
    -0.78
    contentLoaded
    -0.74
    InstanceState
    -0.73
    AddTagHelper
    -0.73
     BorderSide
    -0.72
     发表于
    -0.71
    SequentialGroup
    -0.70
     cherchez
    -0.70
    POSITIVE LOGITS
     ")[
    0.57
    isable
    0.51
     spett
    0.51
     wa
    0.48
    iration
    0.48
     "));
    0.48
     <>",
    0.46
     genommen
    0.45
    quotation
    0.45
    ı
    0.45
    Act Density 0.001%

    No Known Activations