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

    Neuronpedia

    INDEX
    Explanations

    words related to changes in quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "in" followed by numerical data or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.88
    fab
    -0.75
    fuck
    -0.75
    Planet
    -0.73
    aldi
    -0.72
    Sham
    -0.72
    leon
    -0.72
    »Ĵ
    -0.71
    spring
    -0.70
    woods
    -0.69
    POSITIVE LOGITS
     popularity
    1.14
    efficiency
    1.01
     incidence
    0.99
     productivity
    0.98
     activity
    0.96
     revenues
    0.95
     competitiveness
    0.90
     revenue
    0.90
     prevalence
    0.89
     profitability
    0.89
    Act Density 0.096%

    No Known Activations