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

    Neuronpedia

    INDEX
    Explanations

    references to "the" in various contexts

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

    Year, Day, Month, or Month names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    daß
    -0.51
     cherchés
    -0.45
    cektir
    -0.44
     orina
    -0.43
     zrobić
    -0.42
    //
    -0.41
    นะครับ
    -0.41
     Grüsse
    -0.39
    jenige
    -0.39
    koliv
    -0.38
    POSITIVE LOGITS
    OfThe
    0.51
     Touchable
    0.48
    يكب
    0.48
    <bos>
    0.47
    ofthe
    0.47
     titration
    0.47
     Czechos
    0.46
     trun
    0.46
     Вікіпе
    0.46
     Tos
    0.46
    Act Density 0.087%

    No Known Activations