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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or qualifiers in statements

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

    both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellido
    -0.45
    Jep
    -0.42
     JoJo
    -0.42
    clue
    -0.41
    Chapman
    -0.41
    rapeau
    -0.41
    Chao
    -0.41
    AFC
    -0.40
     itſelf
    -0.40
    WLAN
    -0.40
    POSITIVE LOGITS
    ทั้ง
    1.58
     ทั้ง
    1.20
    ทุก
    0.71
     både
    0.68
    ตั้ง
    0.58
     both
    0.57
     المعيارى
    0.56
     além
    0.56
     naast
    0.56
    หลาย
    0.55
    Act Density 0.001%

    No Known Activations