INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     springs
    -0.08
     gew
    -0.08
     Gaulle
    -0.08
    	change
    -0.08
    >{{
    -0.08
     verandering
    -0.08
    .ctrl
    -0.07
    utia
    -0.07
     indrindra
    -0.07
    årt
    -0.07
    POSITIVE LOGITS
    oul
    0.08
    م
    0.08
     मुल
    0.08
     IMS
    0.08
     vrij
    0.07
    oud
    0.07
     livelihoods
    0.07
    uri
    0.07
    0.07
     صد
    0.07
    Act Density 0.005%

    No Known Activations