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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different entities or variables

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comparison."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mic
    -0.74
    jong
    -0.73
    wood
    -0.71
    zyme
    -0.70
    msg
    -0.70
    ieri
    -0.70
    adia
    -0.68
    ighth
    -0.67
     nanop
    -0.67
    ved
    -0.66
    POSITIVE LOGITS
    isons
    0.98
     comparisons
    0.98
     comparison
    0.85
     comparing
    0.83
    ļéĨĴ
    0.81
     Advantage
    0.76
     Compare
    0.76
     favorably
    0.75
    uations
    0.74
     Tsukuyomi
    0.73
    Act Density 0.008%

    No Known Activations