INDEX
    Explanations

    captions or titles of images

    captions associated with images

    New Auto-Interp
    Negative Logits
    vik
    -0.74
    romy
    -0.71
    ult
    -0.62
    ulously
    -0.57
    ounty
    -0.57
     brim
    -0.56
    mil
    -0.56
    crow
    -0.56
    wire
    -0.55
     territ
    -0.54
    POSITIVE LOGITS
     Close
    1.15
     Thumbnails
    0.81
     Caption
    0.77
     Hide
    0.73
     Loading
    0.69
     Controls
    0.68
     partName
    0.67
     Format
    0.65
     Pages
    0.65
    taboola
    0.65
    Act Density 0.026%

    No Known Activations