INDEX
    Explanations

    expressions of greeting or goodwill

    New Auto-Interp
    Negative Logits
    meer
    -0.19
    geber
    -0.17
     gens
    -0.16
    eness
    -0.16
    aven
    -0.15
    ÑĤÑĮ
    -0.15
    weed
    -0.15
    went
    -0.15
    chen
    -0.15
    lover
    -0.14
    POSITIVE LOGITS
    ospace
    0.18
     faith
    0.15
    vard
    0.15
     fore
    0.15
     fun
    0.15
     Buckley
    0.15
    aways
    0.15
     ghost
    0.15
     shown
    0.14
    apesh
    0.14
    Act Density 0.036%

    No Known Activations