INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     succession
    -0.08
     Germany
    -0.07
     Auckland
    -0.07
     Ireland
    -0.07
    atica
    -0.07
     Wimbledon
    -0.07
     caus
    -0.07
     abundant
    -0.07
    .deepEqual
    -0.06
    InstanceOf
    -0.06
    POSITIVE LOGITS
     Irish
    0.29
     Welsh
    0.10
    rish
    0.10
     Norse
    0.07
    French
    0.07
    ish
    0.07
    ISH
    0.07
     DIR
    0.06
    Ir
    0.06
    	sys
    0.06
    Act Density 0.002%

    No Known Activations