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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     agreements
    1.16
     Necklace
    1.13
    ❤️❤️
    1.13
    玝
    1.13
     struts
    1.11
     Möglich
    1.10
     débil
    1.10
     ganze
    1.09
     أصبح
    1.08
    సాగ
    1.07
    POSITIVE LOGITS
    ת
    1.74
    s
    1.63
    ن
    1.56
    ات
    1.48
    ع
    1.48
    ي
    1.42
    ان
    1.38
    ের
    1.37
    י
    1.34
    ad
    1.34
    Act Density 1.192%

    No Known Activations