INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sentence
    -0.14
     synonyms
    -0.12
     sentences
    -0.12
     pron
    -0.11
     Pron
    -0.11
     Sentence
    -0.11
     syntax
    -0.11
     phrase
    -0.10
    åı¥
    -0.10
     synonym
    -0.10
    POSITIVE LOGITS
     ending
    0.16
     irregular
    0.16
     inf
    0.16
     endings
    0.16
     Ending
    0.16
    Ending
    0.14
     forms
    0.14
    forms
    0.14
     morph
    0.14
     Morph
    0.13
    Act Density 0.077%

    No Known Activations