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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "while" indicating ongoing actions or conditions

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

    during an activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     članak
    -0.45
    Viited
    -0.39
     ISNI
    -0.35
    AdapterFactory
    -0.35
     fjer
    -0.33
    delmi
    -0.33
     disponibilidad
    -0.33
     ddelweddau
    -0.32
    Gweler
    -0.32
     hué
    -0.32
    POSITIVE LOGITS
     tijdens
    0.68
     podczas
    0.63
     أثناء
    0.61
     trakcie
    0.59
     during
    0.59
    during
    0.58
     هنگام
    0.57
    หว่าง
    0.55
     durante
    0.54
    beim
    0.54
    Act Density 0.191%

    No Known Activations