INDEX
    Explanations

    conjunctions and related connecting words in sentences

    New Auto-Interp
    Negative Logits
    ites
    -0.17
    unsch
    -0.17
     versus
    -0.15
    988
    -0.14
     tot
    -0.14
    TF
    -0.14
     Produce
    -0.14
    оÑĢе
    -0.13
     pir
    -0.13
    owski
    -0.13
    POSITIVE LOGITS
     eskort
    0.18
     whose
    0.16
    whose
    0.16
    ayi
    0.15
    ILLISE
    0.15
    obe
    0.15
    åĩ
    0.15
    รม
    0.15
    ufen
    0.15
    llen
    0.15
    Act Density 0.027%

    No Known Activations