INDEX
    Explanations

    mentions of the Apple brand

    New Auto-Interp
    Negative Logits
    naire
    -0.19
    geh
    -0.17
    emaker
    -0.17
    elor
    -0.16
    wers
    -0.15
    opoulos
    -0.15
    gem
    -0.15
    fty
    -0.14
    naires
    -0.14
    oppers
    -0.14
    POSITIVE LOGITS
    bee
    0.28
     cider
    0.24
    ton
    0.23
    baum
    0.22
    seed
    0.22
    auce
    0.21
    jack
    0.21
    Care
    0.19
     Maps
    0.19
     Footer
    0.18
    Act Density 0.010%

    No Known Activations