INDEX
    Explanations

    SQL queries

    New Auto-Interp
    Negative Logits
    _normalized
    -0.07
     respir
    -0.07
     samen
    -0.07
    _DAMAGE
    -0.07
    _serv
    -0.07
     bilir
    -0.06
     heatmap
    -0.06
    Interfaces
    -0.06
     věcí
    -0.06
     язы
    -0.06
    POSITIVE LOGITS
     CTRL
    0.06
    	dt
    0.06
    iteration
    0.06
     доктор
    0.06
     Fortnite
    0.05
    TypeEnum
    0.05
    ,更
    0.05
     distinguished
    0.05
    (from
    0.05
    ymology
    0.05
    Act Density 0.005%

    No Known Activations