INDEX
    Explanations

    the preposition "to" in various contexts throughout the text

    New Auto-Interp
    Negative Logits
     attempt
    -0.21
     attempts
    -0.21
    attempt
    -0.17
     Attempts
    -0.16
     try
    -0.16
    iene
    -0.15
    à¸ŀย
    -0.15
     attempted
    -0.15
    uxe
    -0.14
    Attempts
    -0.14
    POSITIVE LOGITS
    er
    0.16
    ed
    0.15
    WAYS
    0.15
    293
    0.15
    283
    0.14
    äºĨä¸Ģ
    0.14
    614
    0.14
    çļĦæĺ¯
    0.14
    983
    0.14
    040
    0.14
    Act Density 0.051%

    No Known Activations