INDEX
    Explanations

    references to education and artistic training

    New Auto-Interp
    Negative Logits
    osy
    -0.15
    STEM
    -0.15
    ürk
    -0.14
    elay
    -0.14
    iam
    -0.14
    òng
    -0.14
     Zaman
    -0.14
    ahan
    -0.14
    acente
    -0.13
    rescia
    -0.13
    POSITIVE LOGITS
     studios
    0.21
     studio
    0.20
     tut
    0.19
     Practical
    0.18
     Studios
    0.18
     Studio
    0.17
     audition
    0.16
    studio
    0.16
     classes
    0.15
    -validate
    0.14
    Act Density 0.064%

    No Known Activations