INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Lomb
    -0.89
    SharedDtor
    -0.78
     WaitForSeconds
    -0.77
    moiselle
    -0.75
    twimg
    -0.74
    érfi
    -0.72
    
    -0.72
     kasarigan
    -0.71
    
    -0.71
     auffi
    -0.70
    POSITIVE LOGITS
     Bridge
    1.90
     bridge
    1.87
    bridge
    1.73
    Bridge
    1.70
     bridges
    1.62
     BRIDGE
    1.62
     Bridges
    1.50
    BRIDGE
    1.38
    bridges
    1.37
     puente
    1.25
    Act Density 0.037%

    No Known Activations