INDEX
    Explanations

    in phrases like "in terms" or "in order"

    New Auto-Interp
    Negative Logits
     Person
    0.44
    Person
    0.42
    ostrat
    0.42
     preceded
    0.40
     Proble
    0.39
     PERSON
    0.38
    )}\
    0.38
    proble
    0.38
     Personen
    0.38
     predecessors
    0.37
    POSITIVE LOGITS
     accordance
    0.67
     terms
    0.61
     unison
    0.60
     spite
    0.60
     maniera
    0.59
     vain
    0.56
     disguise
    0.54
     Malayalam
    0.52
     términos
    0.52
     ways
    0.52
    Act Density 0.015%

    No Known Activations