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

    Neuronpedia

    INDEX
    Explanations

    polite expressions of gratitude or closing salutations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Formal email closings

    np_acts-logits-general · gemini-2.0-flash

    closing salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.76
    $.
    -0.72
    '}>
    -0.71
    >())
    -0.69
    "}>
    -0.69
    !")
    -0.67
    newBuilder
    -0.67
    MessageOf
    -0.66
    '},
    -0.66
    ’).
    -0.66
    POSITIVE LOGITS
    ↵
    0.91
    ↵↵
    0.79
                                   
    0.65
    ↵↵↵
    0.65
    <eos>
    0.57
    InstrumentedTest
    0.55
    ,
    0.54
    Yours
    0.54
    ViewImports
    0.53
                       
    0.52
    Act Density 0.162%

    No Known Activations