INDEX
    Explanations

    captions in news articles or images

    instances of captions or titles associated with images

    New Auto-Interp
    Negative Logits
    bers
    -0.74
    abol
    -0.69
    vik
    -0.68
    romy
    -0.67
    nesia
    -0.64
    ult
    -0.64
     brim
    -0.63
    bery
    -0.63
    ber
    -0.62
    rers
    -0.61
    POSITIVE LOGITS
     Close
    1.02
     Caption
    0.91
     Thumbnails
    0.86
     Shutdown
    0.81
     Loading
    0.80
     ï
    0.71
     captcha
    0.71
     partName
    0.69
     Highlights
    0.68
     Preferences
    0.68
    Act Density 0.022%

    No Known Activations