references to characters or terms related to the Star Wars franchise
    Neuronpedia logo
    GPT2-SMALL
    0-RES-JB
    INDEX 14057
    Negative Logits
    Murray
    -0.89
     Murray
    -0.83
     Pound
    -0.83
     Paula
    -0.80
    Portland
    -0.75
     Beaver
    -0.72
     Gilbert
    -0.71
     Gö
    -0.69
    Jenn
    -0.68
     Portland
    -0.68
    POSITIVE LOGITS
     Jedi
    3.20
     lightsaber
    2.85
     Leia
    2.84
     Sith
    2.81
     Darth
    2.49
     Kenobi
    2.46
     Vader
    2.45
     Skywalker
    2.39
     droid
    2.37
     Obi
    2.31
    Act Density 0.057%

    No Known Activations