INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    що
    -0.07
    izzo
    -0.07
     optic
    -0.07
     suspect
    -0.07
     aşağıdaki
    -0.07
    _Node
    -0.07
     cron
    -0.07
     note
    -0.07
     sampled
    -0.06
    -0.06
    POSITIVE LOGITS
     build
    0.13
     built
    0.12
     Building
    0.11
     building
    0.11
    Build
    0.11
    build
    0.10
     Build
    0.10
     Builder
    0.09
     Built
    0.09
    Built
    0.09
    Act Density 0.065%

    No Known Activations