INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    iams
    -0.17
    igner
    -0.15
    emente
    -0.14
    ÏĢά
    -0.14
    i
    -0.14
    \":{\"
    -0.14
    uÅŁ
    -0.14
     terminal
    -0.14
    elia
    -0.14
    yi
    -0.14
    POSITIVE LOGITS
    oleon
    0.28
     Nap
    0.24
    flix
    0.20
    ster
    0.19
     nap
    0.18
    leon
    0.17
    kins
    0.17
    weed
    0.16
    alm
    0.16
    olean
    0.16
    Act Density 0.009%

    No Known Activations