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

    Neuronpedia

    INDEX
    Explanations

    statistics related to percentage changes in various metrics, such as crime rates and economic indicators

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statistics and data regarding changes in rates or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     authent
    -0.75
    authent
    -0.70
     obsess
    -0.66
     cart
    -0.66
     crap
    -0.66
     badass
    -0.65
     stuff
    -0.64
    Ħ¢
    -0.63
    ente
    -0.63
    ocene
    -0.62
    POSITIVE LOGITS
     Adjusted
    0.96
    Decre
    0.89
    Increase
    0.89
     compared
    0.87
    Ranked
    0.87
     (âĪĴ
    0.86
     Decre
    0.85
     tripled
    0.85
     Median
    0.84
     unemployment
    0.83
    Act Density 0.452%

    No Known Activations