INDEX
    Explanations

    references to various forms of painting and paint-related activities

    New Auto-Interp
    Negative Logits
    erator
    -0.18
    rint
    -0.16
    hf
    -0.15
    ogn
    -0.15
    eration
    -0.15
    ожеÑĤ
    -0.15
    naments
    -0.15
    hai
    -0.15
    Sink
    -0.15
     Sink
    -0.15
    POSITIVE LOGITS
    brush
    0.29
    ings
    0.20
    staking
    0.19
    (Paint
    0.17
    balls
    0.15
    istry
    0.15
     brush
    0.14
    .googleapis
    0.14
    dex
    0.14
    oons
    0.14
    Act Density 0.020%

    No Known Activations