INDEX
    Explanations

    punctuation marks, specifically periods

    New Auto-Interp
    Negative Logits
     Joey
    -0.17
    ække
    -0.15
     Russ
    -0.14
     Russell
    -0.14
     Rus
    -0.14
    udget
    -0.13
     Jackson
    -0.13
     im
    -0.13
     James
    -0.13
    _GPU
    -0.13
    POSITIVE LOGITS
    0
    0.34
    Û°
    0.16
    âĤĢ
    0.16
    1
    0.15
    Ïĥι
    0.15
    uther
    0.15
    weg
    0.14
     rád
    0.14
     Emit
    0.14
    zan
    0.14
    Act Density 0.008%

    No Known Activations