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

    Neuronpedia

    INDEX
    Explanations

    words related to different departments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gpu
    -0.74
    ise
    -0.72
    flame
    -0.70
    cest
    -0.67
    ced
    -0.65
    everything
    -0.64
     offline
    -0.62
    nob
    -0.61
    raise
    -0.61
    iser
    -0.61
    POSITIVE LOGITS
     Department
    3.53
    Department
    2.90
     Dept
    2.83
     department
    2.44
     departments
    1.98
     Ministry
    1.90
     Bureau
    1.90
     Office
    1.64
     Secretary
    1.61
     Directorate
    1.49
    Act Density 0.019%

    No Known Activations