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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tambien
    0.99
     أيضا
    0.95
     ايضا
    0.95
    なども
    0.93
     myös
    0.89
     также
    0.88
     pueden
    0.87
     mohou
    0.86
     također
    0.86
     môžu
    0.85
    POSITIVE LOGITS
     here
    1.76
     Here
    1.53
    ↵↵
    1.46
    Here
    1.43
    here
    1.32
     HERE
    1.24
    HERE
    1.13
     aquí
    1.11
     aqui
    1.05
     здесь
    1.01
    Act Density 2.508%

    No Known Activations