INDEX
    Explanations

    motorcycle, motorbike, biker, rider

    New Auto-Interp
    Negative Logits
     gymnasium
    0.90
     carat
    0.84
     المصفوف
    0.83
    トマト
    0.80
     pomegranate
    0.79
    PLY
    0.77
    Vectorizer
    0.77
    🍅
    0.77
     playwright
    0.77
     cucumbers
    0.76
    POSITIVE LOGITS
     motorcycle
    2.26
     Motorcycle
    2.13
     biker
    2.03
     bikers
    1.97
     motorbike
    1.96
     motorcycles
    1.95
     Motorcycles
    1.94
     motorcycl
    1.93
     rider
    1.92
     bike
    1.90
    Act Density 0.123%

    No Known Activations