INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Shooter
    -0.50
    -0.48
     spé
    -0.48
     ListTile
    -0.47
    gero
    -0.47
     Pep
    -0.46
    teardown
    -0.46
    ichio
    -0.46
    +#+#
    -0.46
    Toponymie
    -0.46
    POSITIVE LOGITS
     France
    1.78
    France
    1.70
     FRANCE
    1.41
     france
    1.38
    france
    1.36
    FRANCE
    1.27
     Frankreich
    1.21
     França
    1.11
     Francia
    1.10
     Frankrijk
    1.10
    Act Density 0.005%

    No Known Activations