INDEX
    Explanations

    mentions of the social media platform Facebook

    New Auto-Interp
    Negative Logits
    Boom
    -0.15
    vala
    -0.15
     framebuffer
    -0.14
    rolled
    -0.14
    WebKit
    -0.14
    Ľå»º
    -0.14
    rowsable
    -0.14
    gii
    -0.14
    ÅĻev
    -0.14
     kt
    -0.14
    POSITIVE LOGITS
    tones
    0.16
    ENCH
    0.16
    еÑĤÑĭ
    0.16
    .Strict
    0.15
    注
    0.15
    venir
    0.14
     hearts
    0.14
     brains
    0.14
    spacer
    0.14
    vk
    0.14
    Act Density 0.018%

    No Known Activations