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

    Neuronpedia

    INDEX
    Explanations

    numbers, specifically those related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 190 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olf
    -0.83
    lying
    -0.80
    matic
    -0.76
    vest
    -0.76
    aming
    -0.75
    mond
    -0.74
    agged
    -0.72
    âĹ¼
    -0.72
    aiden
    -0.71
    printed
    -0.71
    POSITIVE LOGITS
     kHz
    0.85
    kHz
    0.84
    âĸĪ
    0.79
     ILCS
    0.78
    ãĥ¼ãĤ¯
    0.74
     Deg
    0.73
     inhibitors
    0.70
    ĨĴ
    0.70
    190
    0.69
     inhibitor
    0.68
    Act Density 0.019%

    No Known Activations