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

    Neuronpedia

    INDEX
    Explanations

    numbers with percentage signs

    oai_token-act-pair · gpt-3.5-turbo

    statistics and quantitative data related to rates and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illions
    -0.71
    expensive
    -0.61
    æĸ¹
    -0.60
     purchase
    -0.60
     crowdfunding
    -0.59
    sale
    -0.59
     conting
    -0.58
    ques
    -0.58
     renamed
    -0.58
     datasets
    -0.57
    POSITIVE LOGITS
    %,
    1.20
    %.
    1.20
    %;
    1.12
    %-
    1.01
    %).
    0.87
     ±
    0.85
     msec
    0.83
    %
    0.83
     percent
    0.82
    %)
    0.82
    Act Density 0.132%

    No Known Activations