Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to the Star Wars universe and its characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.56
     bridegroom
    -0.51
    }],
    -0.50
     Daylight
    -0.49
     étudi
    -0.48
     hôtes
    -0.48
    RegressionTest
    -0.48
     hosts
    -0.47
    riwal
    -0.46
     bride
    -0.46
    POSITIVE LOGITS
     Jedi
    0.81
    Jedi
    0.73
     jedi
    0.72
     joaat
    0.70
     Kenobi
    0.69
     Mandalorian
    0.68
     Skywalker
    0.68
    soka
    0.67
     BorderRadius
    0.66
     Yoda
    0.65
    Act Density 0.824%

    No Known Activations