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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mortgages, debt, and financial institutions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bus
    -0.94
    uality
    -0.93
    wagon
    -0.91
     Colbert
    -0.90
    reads
    -0.89
    arity
    -0.87
     Flavoring
    -0.85
     Wilde
    -0.84
    avage
    -0.83
    eming
    -0.83
    POSITIVE LOGITS
     mortgage
    1.07
     mortgages
    1.07
     affordability
    1.00
     foreclosure
    0.96
    chool
    0.91
    ilion
    0.87
     lender
    0.86
     homeowners
    0.85
     insurance
    0.84
     meltdown
    0.84
    Act Density 0.968%

    No Known Activations