INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     equivalently
    0.38
     insistence
    0.38
     junction
    0.37
     Equivalent
    0.36
    Likewise
    0.35
     Transmission
    0.34
     Accepting
    0.33
     Invite
    0.33
     Connection
    0.33
     Interference
    0.33
    POSITIVE LOGITS
     know
    0.64
     us
    0.58
     go
    0.55
     biết
    0.53
    知道
    0.52
     знать
    0.51
    zte
    0.51
     weten
    0.49
     जानते
    0.48
    0.48
    Act Density 0.075%

    No Known Activations