INDEX
    Explanations

    mentions of Donald Trump or references to his name and associated entities

    New Auto-Interp
    Negative Logits
    hetto
    -0.18
     prompt
    -0.15
    ëĦIJ
    -0.14
    omes
    -0.14
    undi
    -0.14
    éĻIJ
    -0.14
    åİħ
    -0.14
    li
    -0.13
    ipop
    -0.13
    ulas
    -0.13
    POSITIVE LOGITS
     Tower
    0.22
     Organization
    0.20
     Towers
    0.20
     tower
    0.17
     Organisation
    0.17
    eters
    0.16
    OWER
    0.16
    tower
    0.16
    eted
    0.15
    Organization
    0.15
    Act Density 0.013%

    No Known Activations