INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Westport
    -0.62
     McIn
    -0.58
     revanche
    -0.57
    firmasi
    -0.56
     Osborn
    -0.53
    setTo
    -0.53
     brune
    -0.51
    cheron
    -0.51
     parcial
    -0.51
    indeki
    -0.50
    POSITIVE LOGITS
    ling
    2.41
    LING
    2.10
    lings
    1.62
    led
    1.53
    les
    1.27
     Ling
    1.27
     ling
    1.26
     LING
    1.24
    Ling
    1.22
    linge
    1.18
    Act Density 0.233%

    No Known Activations