INDEX
    Explanations

    words ending in ive/ent

    New Auto-Interp
    Negative Logits
     feroit
    -0.91
     bénéfices
    -0.90
    bbene
    -0.90
     pleaſure
    -0.90
     varandra
    -0.85
     löyty
    -0.83
     tarko
    -0.83
     mahdol
    -0.83
    зулта
    -0.82
     Majefty
    -0.82
    POSITIVE LOGITS
     note
    0.57
     ex
    0.55
     lit
    0.54
    tan
    0.54
     range
    0.54
     spot
    0.54
    er
    0.53
    mah
    0.52
     dig
    0.52
     ro
    0.51
    Act Density 0.042%

    No Known Activations