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

    Neuronpedia

    INDEX
    Explanations

    specific character sequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     engagements
    -0.71
     aging
    -0.71
     ideal
    -0.70
     ageing
    -0.70
     unprepared
    -0.67
     citiz
    -0.67
     bi
    -0.66
     assassin
    -0.65
     inactive
    -0.65
     sacrificing
    -0.65
    POSITIVE LOGITS
    ³³³³³³³³
    1.09
    ³³³³³³³³³³³³³³³³
    1.05
    PHOTOS
    1.01
    Bus
    0.99
    ³³³³
    0.99
    ³³³
    0.99
    However
    0.93
    Article
    0.91
    RESULTS
    0.91
    Shape
    0.90
    Act Density 0.495%

    No Known Activations