INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    stein
    -0.07
    izziness
    -0.07
     kitten
    -0.06
    Kevin
    -0.06
     kittens
    -0.06
    micro
    -0.06
     persecution
    -0.06
    рения
    -0.06
    Leo
    -0.06
    chair
    -0.06
    POSITIVE LOGITS
     Bond
    0.12
     bond
    0.11
     bonds
    0.11
    Bond
    0.10
     Bonds
    0.10
     bonded
    0.10
     bonding
    0.09
    ond
    0.09
    onds
    0.08
    0.07
    Act Density 0.008%

    No Known Activations