INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Battery
    -0.10
     Battery
    -0.09
     cans
    -0.09
     dryer
    -0.09
     charger
    -0.09
     charg
    -0.09
    _battery
    -0.09
     battery
    -0.09
    åIJĥ
    -0.09
     Washer
    -0.09
    POSITIVE LOGITS
     steam
    0.13
     Steam
    0.12
     machine
    0.12
     NSF
    0.11
     Machine
    0.11
     scales
    0.11
     water
    0.11
    -machine
    0.11
     piercing
    0.11
     Jug
    0.11
    Act Density 0.033%

    No Known Activations