INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     urgently
    -0.09
    urrencies
    -0.08
     össze
    -0.08
    Passengers
    -0.08
     Graves
    -0.08
     Kalou
    -0.07
    -0.07
     LDL
    -0.07
    inees
    -0.07
    _ang
    -0.07
    POSITIVE LOGITS
    体系
    0.10
     yace
    0.09
     filos
    0.08
     medieval
    0.08
     Hipp
    0.08
    0.08
     principles
    0.08
     sayings
    0.08
     принцип
    0.08
     principle
    0.08
    Act Density 0.002%

    No Known Activations