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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     असतात
    1.47
     असते
    1.27
     असतो
    1.21
     থাকে
    1.11
    പ്പെടുന്ന
    1.10
     हुन्छ
    1.02
    始める
    0.97
     ہوتی
    0.96
    ರುತ್ತವೆ
    0.95
     ఉంటాయి
    0.95
    POSITIVE LOGITS
     took
    3.51
     went
    3.46
     did
    3.38
     didn
    3.30
     resulted
    3.10
     was
    3.09
     came
    3.07
    took
    2.89
     Did
    2.89
    Did
    2.89
    Act Density 1.464%

    No Known Activations