INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     wheat
    -0.13
     Wheat
    -0.11
     barley
    -0.11
     shopping
    -0.11
     Dud
    -0.10
     mining
    -0.10
     Disp
    -0.09
     mole
    -0.09
     chem
    -0.09
    ür
    -0.09
    POSITIVE LOGITS
     processing
    0.29
     Processing
    0.26
    -processing
    0.25
     processor
    0.25
    processing
    0.24
    Processing
    0.23
     processors
    0.23
     Processor
    0.22
     processed
    0.21
    Processor
    0.21
    Act Density 0.060%

    No Known Activations