INDEX
    Explanations

    captions or headlines in news articles

    New Auto-Interp
    Negative Logits
    vik
    -0.70
    bers
    -0.70
    abol
    -0.69
    romy
    -0.68
    ult
    -0.65
     brim
    -0.62
    bery
    -0.62
    kered
    -0.61
    kn
    -0.59
    ber
    -0.59
    POSITIVE LOGITS
     Close
    1.03
     Caption
    0.90
     Thumbnails
    0.89
     Shutdown
    0.79
     Loading
    0.78
     ï
    0.71
     captcha
    0.70
     partName
    0.69
     Highlights
    0.69
    Prev
    0.68
    Act Density 0.009%

    No Known Activations