INDEX
    Explanations

    reports of news and stories in particular, often associated with mornings

    references to news reporting and journalism

    New Auto-Interp
    Negative Logits
     commun
    -0.61
     Heath
    -0.54
    oted
    -0.53
    fired
    -0.53
     terminal
    -0.53
     scrimmage
    -0.52
     Evening
    -0.50
     throats
    -0.50
     weap
    -0.50
     distingu
    -0.49
    POSITIVE LOGITS
    annie
    0.65
    enegger
    0.60
    videos
    0.59
    ocobo
    0.59
    hew
    0.59
    ITNESS
    0.59
    ORN
    0.58
    Missing
    0.58
    endif
    0.58
    KO
    0.57
    Act Density 0.055%

    No Known Activations