INDEX
    Explanations

    mentions of social media platforms and their features

    New Auto-Interp
    Negative Logits
    amazon
    -0.18
    .getSelection
    -0.18
     обла
    -0.17
     google
    -0.17
     Amazon
    -0.17
    oogle
    -0.17
    Amazon
    -0.16
     Google
    -0.16
     amazon
    -0.16
     Ing
    -0.15
    POSITIVE LOGITS
    .snap
    0.23
     Discover
    0.18
     Snap
    0.18
     filters
    0.17
     Filters
    0.17
    Snap
    0.17
    >NN
    0.17
     Stories
    0.17
    snap
    0.16
    eph
    0.16
    Act Density 0.022%

    No Known Activations