INDEX
    Explanations

    information related to product descriptions, specifically toy sets and their features

    New Auto-Interp
    Negative Logits
    azi
    -0.16
    ROUGH
    -0.15
    abyrinth
    -0.15
    _OS
    -0.15
    íĸ¥
    -0.15
    ÄŁit
    -0.15
    phem
    -0.15
    ãĤį
    -0.14
    linky
    -0.14
     labyrinth
    -0.14
    POSITIVE LOGITS
     pose
    0.24
     posing
    0.21
     detailed
    0.21
     detailing
    0.21
     sculpt
    0.21
     Pose
    0.20
     detail
    0.20
     artic
    0.20
     posed
    0.19
     details
    0.19
    Act Density 0.007%

    No Known Activations