INDEX
    Explanations

    sentences ending in punctuation

    New Auto-Interp
    Negative Logits
     yem
    -0.15
    eda
    -0.15
    elere
    -0.15
    dens
    -0.14
    hung
    -0.14
    rnd
    -0.14
    oS
    -0.14
    senal
    -0.14
     os
    -0.14
    ardown
    -0.14
    POSITIVE LOGITS
     Esper
    0.17
    swick
    0.15
    983
    0.14
    uns
    0.14
     pur
    0.14
     Uns
    0.14
    oeff
    0.14
    ffer
    0.14
    anch
    0.14
    ARA
    0.14
    Act Density 0.002%

    No Known Activations