INDEX
    Explanations

    the verb "be" in various forms and contexts

    New Auto-Interp
    Negative Logits
    sted
    -0.17
     pickup
    -0.16
    ULER
    -0.16
     odds
    -0.15
     oversh
    -0.15
    onte
    -0.15
    ύ
    -0.15
    ernet
    -0.15
    639
    -0.14
     utility
    -0.14
    POSITIVE LOGITS
    incinn
    0.17
    itler
    0.16
    ihan
    0.15
    çļĦäºĭ
    0.15
     jadx
    0.14
    δι
    0.14
    å¬
    0.14
    ãĥ¼ãĥ
    0.14
    agoon
    0.14
    atri
    0.13
    Act Density 0.555%

    No Known Activations