INDEX
    Explanations

    words related to food and snacks

    New Auto-Interp
    Negative Logits
     Juice
    -0.18
    .appspot
    -0.17
     salad
    -0.17
     Salad
    -0.17
    anni
    -0.17
     sey
    -0.16
    pollo
    -0.16
    олÑİ
    -0.16
     Bubble
    -0.14
     Salisbury
    -0.14
    POSITIVE LOGITS
     cookie
    0.51
     cookies
    0.51
    -cookie
    0.44
     Cookies
    0.43
     Cookie
    0.42
     COOKIE
    0.41
    cookie
    0.40
    cookies
    0.39
    Cookies
    0.39
    Cookie
    0.36
    Act Density 0.029%

    No Known Activations