INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Grape
    -0.07
    -0.06
     suspicion
    -0.06
    ."↵
    -0.06
     masculine
    -0.06
     Spokane
    -0.06
    ويس
    -0.06
     Degree
    -0.06
    _Button
    -0.06
     tohoto
    -0.06
    POSITIVE LOGITS
     Bankası
    0.07
     ville
    0.06
     cins
    0.06
    ('../../
    0.06
    0.06
    .StylePriority
    0.06
    ':[
    0.06
     linebacker
    0.06
    нить
    0.06
    atra
    0.06
    Act Density 0.017%

    No Known Activations