INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Table
    -0.07
     bajo
    -0.07
     covers
    -0.07
    ple
    -0.06
    Secure
    -0.06
    Byte
    -0.06
     Tree
    -0.06
     após
    -0.06
    chedule
    -0.06
    	head
    -0.06
    POSITIVE LOGITS
    ism
    0.20
    ISM
    0.15
    ismo
    0.13
    isme
    0.11
    ivism
    0.10
     realism
    0.10
    isms
    0.10
     nationalism
    0.10
    atism
    0.09
    izm
    0.09
    Act Density 0.021%

    No Known Activations