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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    Follows expressions of gratitude or condolences

    np_acts-logits-general · gemini-2.0-flash

    gratitude and condolences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.83
    <bos>
    -0.69
    Personendaten
    -0.64
    OrNil
    -0.64
    Спољашње
    -0.62
    Искәрмәләр
    -0.60
    تقاوى
    -0.60
    RenderAtEndOf
    -0.59
    èdia
    -0.55
     externi
    -0.55
    POSITIVE LOGITS
     May
    1.37
    May
    1.32
     may
    1.26
    may
    1.12
     God
    0.97
     Thank
    0.96
     Rest
    0.94
     MAY
    0.94
    Rest
    0.90
    God
    0.90
    Act Density 0.128%

    No Known Activations