INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cable
    -2.75
     Cable
    -2.47
    Cable
    -2.47
    cable
    -2.33
     CABLE
    -2.16
     câble
    -1.68
     cables
    -1.60
     Cables
    -1.55
    ケーブル
    -1.48
    cables
    -1.48
    POSITIVE LOGITS
    d
    0.59
    e
    0.57
    i
    0.54
    д
    0.51
    ist
    0.51
    k
    0.47
    ous
    0.44
    c
    0.43
    ix
    0.42
    ton
    0.41
    Act Density 1.947%

    No Known Activations