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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters, political affiliations, and military endorsements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Luffy
    -0.70
     Communism
    -0.70
    posts
    -0.67
     Buddhism
    -0.67
    HAM
    -0.66
    Aid
    -0.65
    Apps
    -0.65
     Tasmania
    -0.64
    Scotland
    -0.63
     Zionism
    -0.63
    POSITIVE LOGITS
     same
    1.49
     latter
    1.37
     aforementioned
    1.31
    ses
    1.20
     latest
    1.18
     entire
    1.16
    oret
    1.16
     slightest
    1.07
     biggest
    1.06
     greatest
    1.05
    Act Density 0.119%

    No Known Activations