INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    +#+#
    -0.73
     story
    -0.65
    <_>
    -0.59
    story
    -0.52
     STORY
    -0.50
     narrative
    -0.47
    ]--;
    -0.45
     kool
    -0.44
     Story
    -0.43
    Story
    -0.43
    POSITIVE LOGITS
     of
    0.89
    LEncoder
    0.64
    <bos>
    0.64
    èdia
    0.64
    helves
    0.58
    antMatchers
    0.57
    DataPropertyName
    0.56
    ecap
    0.54
    lets
    0.53
     Waray
    0.53
    Act Density 0.012%

    No Known Activations