INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     investigated
    0.40
     defined
    0.38
    defined
    0.37
    Objectives
    0.36
     Scripts
    0.36
     volatile
    0.36
     expressed
    0.35
     termed
    0.34
    described
    0.34
    volatile
    0.34
    POSITIVE LOGITS
     photos
    1.51
     photographs
    1.46
     фотографии
    1.44
     pictures
    1.43
     사진
    1.41
     photograph
    1.37
    照片
    1.36
     images
    1.30
     fotos
    1.30
     zdjęcia
    1.30
    Act Density 0.070%

    No Known Activations