INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .
    1.24
    affin
    0.86
    یی
    0.81
    ys
    0.80
    ला
    0.80
    ्य
    0.77
     नये
    0.75
    นต์
    0.75
    ett
    0.75
    et
    0.73
    POSITIVE LOGITS
    c
    0.93
    $,
    0.89
     compris
    0.89
     peptides
    0.89
    0.88
     elenco
    0.88
    0.87
    I
    0.87
    。",
    0.86
    ك
    0.85
    Act Density 0.001%

    No Known Activations