INDEX
    Explanations

    social media handles and mentions

    New Auto-Interp
    Negative Logits
     addCriterion
    -0.18
    adÃŃ
    -0.17
    erdale
    -0.14
    ptune
    -0.14
    antz
    -0.14
    tür
    -0.14
     nim
    -0.13
    roup
    -0.13
    sponsor
    -0.13
     Fol
    -0.13
    POSITIVE LOGITS
    chner
    0.18
    iam
    0.15
     Little
    0.14
    ëĦĪ
    0.14
    Ñĩки
    0.14
    طر
    0.14
    .linkedin
    0.14
    ELSE
    0.14
    Agent
    0.13
     Ingen
    0.13
    Act Density 0.023%

    No Known Activations