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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ẞ
    0.54
    ẞ
    0.54
     znovu
    0.51
     erneut
    0.50
    again
    0.50
     wieder
    0.49
    while
    0.45
     আরও
    0.44
    yet
    0.43
    လည်း
    0.43
    POSITIVE LOGITS
    ↵↵
    1.73
    ↵↵↵
    1.13
    ↵↵↵↵
    0.96
     Specifically
    0.94
    ↵
    0.89
     Essentially
    0.85
    ↵↵↵↵↵
    0.85
     Basically
    0.83
    <0x0D>
    0.70
     Namely
    0.68
    Act Density 2.027%

    No Known Activations