INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     SKF
    -0.07
     rijdt
    -0.07
     οδηγ
    -0.07
     vliegt
    -0.07
     rere
    -0.07
     straighten
    -0.07
     führ
    -0.07
    -0.07
     WAV
    -0.07
     airborne
    -0.07
    POSITIVE LOGITS
     accueillir
    0.09
    .gov
    0.08
    meler
    0.07
    (empty
    0.07
     Moi
    0.07
    /trans
    0.07
     Mae
    0.07
     Berger
    0.07
    /Foundation
    0.07
     permiss
    0.07
    Act Density 0.012%

    No Known Activations