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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ên
    1.30
    ंसाठी
    1.28
    所谓的
    1.24
    ant
    1.20
     смеси
    1.20
    ail
    1.18
    istance
    1.18
    َات
    1.17
    ém
    1.16
    olution
    1.16
    POSITIVE LOGITS
    tı
    2.06
    ます
    2.02
    تها
    2.02
    t
    2.00
    tze
    1.93
    ्ज
    1.88
    ת
    1.85
    ्ड
    1.84
    ्स
    1.83
    ますが
    1.83
    Act Density 0.187%

    No Known Activations