INDEX
    Explanations

    URLs, specifically those linking to YouTube videos

    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.85
     ProtoMessage
    -0.83
     mergeFrom
    -0.76
     disambiguazione
    -0.70
    Бахар
    -0.67
     Meksiku
    -0.65
    WebElementEntity
    -0.65
     Geraadpleegd
    -0.64
    elemField
    -0.61
     internetowa
    -0.59
    POSITIVE LOGITS
    watch
    0.60
     watch
    0.57
     laure
    0.48
     Bulbs
    0.47
     user
    0.47
    extAlignment
    0.46
    Prest
    0.46
    orative
    0.46
    attribution
    0.45
     دیدن
    0.45
    Act Density 0.063%

    No Known Activations