INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    reiben
    -0.06
     gs
    -0.06
     Targets
    -0.06
    uhn
    -0.06
     ves
    -0.06
    ---
    -0.06
    -0.06
    .rs
    -0.06
     acordo
    -0.06
     targets
    -0.06
    POSITIVE LOGITS
     had
    0.09
     Has
    0.08
     have
    0.08
     has
    0.08
    Has
    0.07
    had
    0.07
     wont
    0.07
     haven
    0.07
    >r
    0.07
     HAS
    0.07
    Act Density 0.080%

    No Known Activations