INDEX
    Explanations

    the word "right" used in various contexts

    New Auto-Interp
    Negative Logits
     shorthand
    -0.17
    heim
    -0.16
    amp
    -0.15
    .reporting
    -0.14
    keley
    -0.14
    ockets
    -0.14
    ycz
    -0.14
    ils
    -0.14
    ucer
    -0.14
    rq
    -0.13
    POSITIVE LOGITS
    eous
    0.23
    e
    0.23
    eo
    0.23
    fully
    0.22
    wing
    0.20
    ToLeft
    0.20
    -sizing
    0.20
    -wing
    0.19
     wing
    0.18
    -click
    0.17
    Act Density 0.028%

    No Known Activations