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

    Neuronpedia

    INDEX
    Explanations

    references to dates, specifically mentioning the word "day."

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

    days and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.57
    Tikang
    -0.47
    apropri
    -0.47
     ממ
    -0.45
     muun
    -0.44
    Namara
    -0.43
     eikä
    -0.43
     vastaan
    -0.41
    mapsto
    -0.41
    ajaan
    -0.40
    POSITIVE LOGITS
    日
    2.11
     日
    1.66
    日的
    1.21
    の日
    1.08
    日在
    0.98
    일
    0.95
    日は
    0.92
    日の
    0.92
    日を
    0.91
     day
    0.90
    Act Density 0.001%

    No Known Activations