INDEX
    Explanations

    mentions of Donald Trump and related terms

    New Auto-Interp
    Negative Logits
    -bodied
    -0.15
    vez
    -0.15
    umen
    -0.14
    ecom
    -0.14
    gers
    -0.14
    ÏģοÏħ
    -0.14
    erd
    -0.14
    umlu
    -0.14
    ifestyle
    -0.14
    ogy
    -0.13
    POSITIVE LOGITS
    nat
    0.17
    enstein
    0.17
    olvency
    0.16
    s
    0.16
    ollider
    0.15
    linger
    0.15
    Nat
    0.15
    .LookAndFeel
    0.15
    PFN
    0.15
    _PTR
    0.15
    Act Density 0.024%

    No Known Activations