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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to publishing, documents, and information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Administ
    -0.57
    itect
    -0.55
    iqueness
    -0.52
    addin
    -0.52
    swing
    -0.51
    ¿½
    -0.51
    hesda
    -0.51
    leon
    -0.50
    «
    -0.50
     architects
    -0.50
    POSITIVE LOGITS
    prints
    0.77
     freely
    0.76
     newsletters
    0.74
     DVDs
    0.72
     copies
    0.71
     transcripts
    0.71
     onto
    0.70
    20439
    0.69
     batches
    0.69
     secrets
    0.68
    Act Density 23.066%

    No Known Activations