INDEX
    Explanations

    mentions of electronic devices, particularly laptops

    New Auto-Interp
    Negative Logits
    tale
    -0.84
    Relations
    -0.73
    reek
    -0.72
    κ
    -0.72
    alez
    -0.71
    UCT
    -0.66
    ribune
    -0.65
    sche
    -0.65
    relations
    -0.65
    iosyncr
    -0.64
    POSITIVE LOGITS
     laptops
    0.96
    aptop
    0.94
     laptop
    0.92
     computers
    0.89
    intosh
    0.88
    pad
    0.82
     MacBook
    0.81
     charger
    0.80
     PCs
    0.77
     CPUs
    0.77
    Act Density 0.038%

    No Known Activations