INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     downtown
    0.74
     Downtown
    0.72
     Mecca
    0.68
     Har
    0.67
    owntown
    0.63
     Melrose
    0.63
     London
    0.62
     elabor
    0.61
     Louvre
    0.61
     Marseille
    0.61
    POSITIVE LOGITS
    putBoolean
    1.87
    Boolean
    1.86
    bool
    1.71
    是否
    1.70
     Boolean
    1.69
     bool
    1.69
    Bool
    1.64
    boolean
    1.64
     toggle
    1.61
     是否
    1.61
    Act Density 0.835%

    No Known Activations