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

    Neuronpedia

    INDEX
    Explanations

    titles of news articles with various topics

    oai_token-act-pair · gpt-3.5-turbo

    various statistics and reports about societal issues or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.64
     Architects
    -0.63
     compe
    -0.61
     honoured
    -0.60
    ttes
    -0.60
     altar
    -0.60
     behaviour
    -0.59
     substitute
    -0.59
     oxid
    -0.57
     initi
    -0.57
    POSITIVE LOGITS
    advertisement
    0.93
    Sensor
    0.87
     Caption
    0.86
    ccording
    0.86
    Related
    0.85
    Prof
    0.83
    inventoryQuantity
    0.82
    Meanwhile
    0.82
    Similar
    0.81
    Article
    0.80
    Act Density 0.132%

    No Known Activations