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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to the population or its percentage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.72
    RAW
    -0.70
    æ³
    -0.69
    PLA
    -0.68
    qi
    -0.66
    edd
    -0.65
    arya
    -0.61
    ful
    -0.60
    rade
    -0.60
    pecially
    -0.60
    POSITIVE LOGITS
     country
    0.95
     nation
    0.94
     populace
    0.91
     heaviest
    0.88
     population
    0.85
     smallest
    0.85
     electorate
    0.84
     spectrum
    0.82
     remainder
    0.81
     workforce
    0.79
    Act Density 0.172%

    No Known Activations