INDEX
    Explanations

    hyperlinks to social media platforms, particularly highlighting Pinterest with varying degrees of emphasis

    mentions of the social media platform Pinterest

    New Auto-Interp
    Negative Logits
    phas
    -0.74
    hood
    -0.70
    ppo
    -0.70
    perse
    -0.68
     Hague
    -0.67
    enegger
    -0.65
    holm
    -0.64
    lves
    -0.64
    isen
    -0.63
     Luxem
    -0.62
    POSITIVE LOGITS
    Pinterest
    1.02
     Pinterest
    0.90
    LinkedIn
    0.83
    Filter
    0.80
     PHOTO
    0.79
    sylv
    0.78
    avascript
    0.77
    User
    0.77
    icket
    0.72
    Tumblr
    0.71
    Act Density 0.004%

    No Known Activations