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

    Neuronpedia

    INDEX
    Explanations

    references to quantitative metrics or rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parsons
    -0.86
     Donaldson
    -0.70
     Montserrat
    -0.70
     pann
    -0.69
     Cleary
    -0.67
     avs
    -0.66
    Edmund
    -0.66
     فريبيس
    -0.65
    livion
    -0.65
    पु
    -0.64
    POSITIVE LOGITS
     rates
    1.65
     Rates
    1.46
     rate
    1.46
     Rate
    1.45
     RATE
    1.40
    Rates
    1.39
    Rate
    1.35
     RATES
    1.27
    RATE
    1.20
    rate
    1.14
    Act Density 0.082%

    No Known Activations