INDEX
    Explanations

    transitional phrases and contrasting conjunctions

    New Auto-Interp
    Negative Logits
    ALI
    -0.14
    alli
    -0.14
    awei
    -0.13
    ogan
    -0.13
    ali
    -0.13
    culate
    -0.13
     subjective
    -0.13
    °
    -0.13
    .Cart
    -0.13
    illy
    -0.13
    POSITIVE LOGITS
     only
    0.19
     differently
    0.17
    주ìĿĺ
    0.16
     upside
    0.16
     it
    0.16
     nowhere
    0.15
    ãģĿãĤĮãģ¯
    0.15
     ONLY
    0.14
    onio
    0.14
    mium
    0.14
    Act Density 0.206%

    No Known Activations