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

    Neuronpedia

    INDEX
    Explanations

    keywords related to media content, news articles, and actions related to accountability

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to media, storytelling, and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.76
     Caucus
    -0.73
    cium
    -0.67
     Mississ
    -0.67
    ystem
    -0.62
     Roads
    -0.62
     Lank
    -0.62
    âĦ¢
    -0.61
     Settlement
    -0.61
    ECD
    -0.61
    POSITIVE LOGITS
     wise
    1.03
    wise
    0.97
    lessly
    0.89
    ally
    0.87
    fully
    0.85
    ually
    0.82
    arily
    0.81
    ically
    0.81
    less
    0.75
     versa
    0.74
    Act Density 0.407%

    No Known Activations