INDEX
    Explanations

    terms associated with name changes and identity

    New Auto-Interp
    Negative Logits
    RTCF
    -0.40
     uy
    -0.38
    netbeans
    -0.36
    giphy
    -0.36
    CPtr
    -0.35
    hoeddwyd
    -0.35
     Ind
    -0.35
    mouth
    -0.35
     Giải
    -0.35
     ар
    -0.34
    POSITIVE LOGITS
     myſelf
    0.50
     againſt
    0.49
     originais
    0.48
     femininas
    0.48
    jména
    0.48
     raiſ
    0.48
     faſt
    0.47
    rungsseite
    0.47
     itſelf
    0.47
    pecabezas
    0.45
    Act Density 0.343%

    No Known Activations