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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" in various contexts

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

    Followed by stop words: a, the, in

    np_acts-logits-general · gemini-2.0-flash

    articles referencing lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -1.23
    StoreMessageInfo
    -1.06
     nakalista
    -1.05
    Geplaatst
    -1.03
    Jereo
    -0.96
     ویکی‌پدیا
    -0.94
    Архівовано
    -0.92
    Билгалдахарш
    -0.91
    RectangleBorder
    -0.90
     ErrIntOverflow
    -0.90
    POSITIVE LOGITS
    ↵↵↵
    0.46
    afone
    0.44
    </em>
    0.44
      
    0.41
     even
    0.40
    ailleurs
    0.39
    ↵
    0.38
    قيقة
    0.38
    また
    0.38
     Are
    0.37
    Act Density 0.547%

    No Known Activations