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

    Neuronpedia

    INDEX
    Explanations

    mentions of countries and specific locations within a document

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unbeliev
    -0.95
    clusively
    -0.90
     nodd
    -0.88
    sworth
    -0.88
    ciating
    -0.87
     glim
    -0.87
    ctive
    -0.86
    spons
    -0.85
    aturdays
    -0.85
    \":
    -0.85
    POSITIVE LOGITS
     Airlines
    1.19
    oslov
    1.01
     Airways
    1.00
     Border
    0.94
     Telecom
    0.89
     Pavilion
    0.88
     Yard
    0.84
     Secret
    0.83
     Alps
    0.80
     border
    0.80
    Act Density 1.583%

    No Known Activations