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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and technical terms related to labor unions, politics, and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    urally
    -0.85
    andestine
    -0.85
    ortium
    -0.78
    inyl
    -0.76
    isitions
    -0.71
    iferation
    -0.69
    ysis
    -0.69
    ossibility
    -0.69
     restrooms
    -0.67
     restroom
    -0.67
    POSITIVE LOGITS
    wire
    1.12
    stack
    0.99
    nes
    0.94
    leigh
    0.94
    maker
    0.88
    ley
    0.87
    makers
    0.85
    hawks
    0.84
    elin
    0.83
    den
    0.82
    Act Density 6.655%

    No Known Activations