INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .Ass
    -0.08
    -0.08
    ïde
    -0.08
     appearing
    -0.08
    чес
    -0.08
    .Aggreg
    -0.07
    naire
    -0.07
     vector
    -0.07
     datum
    -0.07
     sain
    -0.07
    POSITIVE LOGITS
     infrared
    0.08
    infra
    0.08
    _low
    0.08
    quiet
    0.08
     Spot
    0.08
    _ESCAPE
    0.08
    .SP
    0.07
     הקר
    0.07
     चेहरे
    0.07
     incandescent
    0.07
    Act Density 0.012%

    No Known Activations