INDEX
    Explanations

    references to physical substances and materials

    New Auto-Interp
    Negative Logits
     canv
    -0.16
    ols
    -0.15
    d
    -0.14
    chner
    -0.14
     Holt
    -0.14
    inou
    -0.14
    rk
    -0.14
     Mis
    -0.14
    start
    -0.14
    in
    -0.13
    POSITIVE LOGITS
    orne
    0.15
    ADDE
    0.15
    æį
    0.14
     вокÑĢÑĥг
    0.14
     ÑĤол
    0.14
    INESS
    0.14
    ibri
    0.14
     autour
    0.14
    ancybox
    0.14
    ertia
    0.14
    Act Density 0.098%

    No Known Activations