INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     engineers
    -0.08
     opinion
    -0.06
     viewpoint
    -0.06
     campuses
    -0.06
     Fallon
    -0.06
     scores
    -0.06
    edeyse
    -0.06
     contends
    -0.06
     như
    -0.06
     locker
    -0.06
    POSITIVE LOGITS
     pirates
    0.07
    LEC
    0.07
    breaker
    0.07
     Pig
    0.06
     Met
    0.06
     outright
    0.06
    aire
    0.06
    scoped
    0.06
    τική
    0.06
     bitmap
    0.06
    Act Density 0.004%

    No Known Activations