INDEX
    Explanations

    references to color and shading in various contexts

    New Auto-Interp
    Negative Logits
     redhead
    -0.18
     beige
    -0.17
    pink
    -0.16
    ebi
    -0.16
     yellow
    -0.15
     crimson
    -0.15
    èħ°
    -0.15
    .yellow
    -0.15
     golden
    -0.15
     orange
    -0.15
    POSITIVE LOGITS
     Blue
    0.63
     blue
    0.62
    Blue
    0.58
     BLUE
    0.57
    blue
    0.56
    -blue
    0.56
    BLUE
    0.50
    _blue
    0.44
    .Blue
    0.44
    èĵĿ
    0.43
    Act Density 0.040%

    No Known Activations