INDEX
    Explanations

    syntactic structures and phrases that indicate comparisons or similarities

    New Auto-Interp
    Negative Logits
     Peters
    -0.16
    icer
    -0.15
    atto
    -0.15
    andler
    -0.15
    Disposition
    -0.15
     Pilot
    -0.15
    ption
    -0.15
    .Symbol
    -0.15
    arov
    -0.14
     Propel
    -0.14
    POSITIVE LOGITS
    iasi
    0.17
    byte
    0.16
    دÙĨ
    0.15
    stadt
    0.15
    oter
    0.15
    -mouth
    0.15
    adores
    0.14
    Ìģt
    0.14
    ارش
    0.14
     dim
    0.14
    Act Density 0.018%

    No Known Activations