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

    Neuronpedia

    INDEX
    Explanations

    references to CNN news articles with varying levels of activations

    oai_token-act-pair · gpt-3.5-turbo

    references to CNN as a news source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rim
    -0.66
     expansion
    -0.64
     Albion
    -0.64
     aesthetic
    -0.63
     pressing
    -0.63
    -[
    -0.62
     numbered
    -0.62
     free
    -0.62
     hop
    -0.62
     Bees
    -0.61
    POSITIVE LOGITS
    CNN
    4.37
     CNN
    2.29
    CBS
    1.56
    CBC
    1.54
    NPR
    1.51
    BBC
    1.48
    ESPN
    1.43
    Bloomberg
    1.40
    Reuters
    1.39
    CDC
    1.39
    Act Density 0.009%

    No Known Activations