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

    Neuronpedia

    INDEX
    Explanations

    specific expressions of greeting, farewell, or personal acknowledgment

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

    closings and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.74
     незавершена
    -0.59
     NUKAT
    -0.54
     Audiodateien
    -0.52
    parsedMessage
    -0.51
     للمعارف
    -0.51
     którzy
    -0.50
    Personendaten
    -0.48
     ostavi
    -0.48
     المعيارى
    -0.48
    POSITIVE LOGITS
    Dear
    0.43
    IContainer
    0.42
    Hey
    0.41
    Beste
    0.38
    ार्थ
    0.37
    TagMode
    0.35
    DEAR
    0.35
    Heya
    0.35
    Hello
    0.34
     YOU
    0.33
    Act Density 0.159%

    No Known Activations