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

    Neuronpedia

    INDEX
    Explanations

    mentions of statistics related to employment, education, and poverty rates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ss
    -0.65
    bugs
    -0.62
     outlaw
    -0.61
     cann
    -0.60
     marines
    -0.60
     oath
    -0.59
    mens
    -0.59
     vend
    -0.59
     heed
    -0.59
    authent
    -0.59
    POSITIVE LOGITS
    verages
    1.01
     averages
    0.95
    Average
    0.92
     averaged
    0.89
     Average
    0.87
    ulia
    0.84
     averaging
    0.82
    Ranked
    0.81
     (âĪĴ
    0.81
    Trend
    0.80
    Act Density 31.724%

    No Known Activations