INDEX
    Explanations

    instances of welcoming and community-themed messages

    New Auto-Interp
    Negative Logits
    orm
    -0.17
     founding
    -0.16
    piel
    -0.15
     Found
    -0.15
    oun
    -0.15
     +
    -0.14
     foundation
    -0.14
    credit
    -0.14
     FOUND
    -0.14
     foundations
    -0.13
    POSITIVE LOGITS
    aurant
    0.17
     Karlov
    0.15
    ãģĭãĤĬ
    0.15
    κÏģα
    0.14
    ebin
    0.14
    uptime
    0.14
    ków
    0.14
    mare
    0.14
    ká
    0.14
    ÄŁan
    0.14
    Act Density 0.042%

    No Known Activations