INDEX
    Explanations

    questions and phrases related to duration or time

    New Auto-Interp
    Negative Logits
    quia
    -0.17
    oki
    -0.16
    faction
    -0.16
    .partial
    -0.15
    iento
    -0.14
    она
    -0.14
    andum
    -0.14
    alto
    -0.14
    座
    -0.13
    kün
    -0.13
    POSITIVE LOGITS
    olist
    0.15
     jue
    0.14
    opher
    0.14
    kke
    0.14
     Friend
    0.14
    .Uint
    0.13
    .signIn
    0.13
    ewise
    0.13
     minor
    0.13
    oran
    0.13
    Act Density 0.015%

    No Known Activations