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

    Neuronpedia

    INDEX
    Explanations

    Japanese particles and conjunctions, particularly those indicating subject or object relationships in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.70
     Mule
    -0.68
     purpoſe
    -0.66
     AVL
    -0.64
     Roch
    -0.64
    あります
    -0.64
     Odon
    -0.64
     Holo
    -0.62
    ौर
    -0.61
    ฐ
    -0.60
    POSITIVE LOGITS
    が
    1.09
    가
    0.98
    りが
    0.94
    리가
    0.91
     が
    0.90
    さが
    0.90
    이
    0.88
    氏が
    0.87
    자가
    0.85
     فريبيس
    0.84
    Act Density 0.023%

    No Known Activations