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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tops
    -0.79
    ebin
    -0.73
    sequence
    -0.68
     delinqu
    -0.66
     landlords
    -0.65
     displeasure
    -0.64
     dwar
    -0.63
    TY
    -0.61
     bruising
    -0.60
     coughing
    -0.60
    POSITIVE LOGITS
     Yard
    0.85
     Liberation
    0.84
     Pavilion
    0.83
    ophobic
    0.80
     Syndrome
    0.80
     Calling
    0.79
     Today
    0.79
     Sunrise
    0.79
     Mortgage
    0.79
     Parables
    0.75
    Act Density 0.143%

    No Known Activations