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

    Neuronpedia

    INDEX
    Explanations

    percentage rates and numerical values related to statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to rates and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸ¹
    -0.64
     Antarctica
    -0.62
     Dos
    -0.60
    illions
    -0.59
    ¥ŀ
    -0.59
    avier
    -0.58
    staking
    -0.54
    expensive
    -0.53
     sund
    -0.53
    imentary
    -0.53
    POSITIVE LOGITS
    %,
    1.65
    %;
    1.55
    %.
    1.51
    %-
    1.43
    %),
    1.25
     percent
    1.23
    %
    1.22
    %).
    1.21
    %:
    1.17
    %)
    1.17
    Act Density 0.127%

    No Known Activations