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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     нет
    0.54
     вами
    0.48
     توی
    0.46
    你在
    0.45
    한테
    0.45
     вас
    0.44
    別人
    0.43
    的是
    0.43
    ]
    0.43
    하세요
    0.43
    POSITIVE LOGITS
     which
    1.13
    which
    1.01
     allowing
    1.00
     necessitating
    0.95
     ensuring
    0.95
     requiring
    0.92
     culminating
    0.91
     vilket
    0.90
     والتي
    0.89
     emphasizing
    0.88
    Act Density 1.033%

    No Known Activations