INDEX
    Explanations

    the infinitive form of verbs

    New Auto-Interp
    Negative Logits
    atest
    -0.16
     Shadows
    -0.15
     swallow
    -0.15
    ÙĪØ²
    -0.15
    iese
    -0.14
    hest
    -0.14
     avanz
    -0.14
    urtle
    -0.14
    mars
    -0.14
     Seconds
    -0.14
    POSITIVE LOGITS
    cha
    0.15
    ABCDEFG
    0.14
    Ù쨧ÙĤ
    0.14
     factorial
    0.14
    agen
    0.14
    ucher
    0.14
    ÙħÙĨت
    0.13
    ÏĮÏģ
    0.13
    olle
    0.13
    umas
    0.13
    Act Density 0.024%

    No Known Activations