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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality, enjoyment, or positive experiences

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

    enjoyment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administration
    -0.40
    administration
    -0.37
    Administration
    -0.36
    angeran
    -0.36
     pracę
    -0.36
     Müll
    -0.36
     dậy
    -0.36
     praca
    -0.35
    工作
    -0.35
     lyst
    -0.35
    POSITIVE LOGITS
     enjoy
    0.96
    enjoy
    0.92
     Enjoy
    0.90
     enjoyed
    0.88
    Enjoy
    0.87
     enjoying
    0.87
     enjoys
    0.86
    Enjoying
    0.79
    MigrationBuilder
    0.78
    ValueStyle
    0.77
    Act Density 0.018%

    No Known Activations