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

    Neuronpedia

    INDEX
    Explanations

    statistical information or data related to percentages and numbers

    oai_token-act-pair · gpt-3.5-turbo

    quantitative statistics related to public opinion or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lamps
    -0.62
     transported
    -0.61
     shiny
    -0.61
     upgrades
    -0.60
     renovations
    -0.60
     evict
    -0.60
     Kafka
    -0.60
     shel
    -0.60
     timelines
    -0.60
     mats
    -0.59
    POSITIVE LOGITS
    thirds
    1.18
    percent
    1.09
     thirds
    1.02
    half
    0.99
    fifth
    0.98
    Percent
    0.96
     percent
    0.95
    third
    0.95
     percentage
    0.94
    quarter
    0.93
    Act Density 0.200%

    No Known Activations