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

    Neuronpedia

    INDEX
    Explanations

    news-related information like photographers, cities, dates, and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Squadron
    -0.67
     relegation
    -0.61
    qs
    -0.60
     probation
    -0.59
     Melee
    -0.57
     Shinra
    -0.57
     runes
    -0.57
     Poké
    -0.56
     grouping
    -0.56
     Xan
    -0.55
    POSITIVE LOGITS
    ccording
    0.80
    BER
    0.79
    ³³³³³³³³³³³³³³³³
    0.78
    Indian
    0.78
    LOS
    0.77
    Washington
    0.76
    umbai
    0.74
    BBC
    0.74
    Dallas
    0.74
    ente
    0.73
    Act Density 0.400%

    No Known Activations