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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values (e.g., quantities or measurements)

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific numerical values in the text, particularly those related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Runtime
    -0.69
     Brennan
    -0.69
     Blake
    -0.68
    oping
    -0.68
     Riley
    -0.68
    ni
    -0.67
     idol
    -0.66
     OC
    -0.65
     imperson
    -0.65
     Yang
    -0.64
    POSITIVE LOGITS
    150
    2.92
     150
    2.19
    1500
    1.66
    130
    1.62
    450
    1.54
     1500
    1.54
    250
    1.52
    550
    1.47
    110
    1.45
    350
    1.45
    Act Density 0.019%

    No Known Activations