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

    Neuronpedia

    INDEX
    Explanations

    names of newspapers and publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newspapers or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaveral
    -0.73
    etime
    -0.73
    abiding
    -0.72
    utical
    -0.70
     pupils
    -0.66
    sed
    -0.65
    gone
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    vae
    -0.65
    liam
    -0.64
    POSITIVE LOGITS
     Tribune
    0.93
     Observer
    0.87
     Editorial
    0.83
     Newspaper
    0.82
     editorial
    0.82
     Archive
    0.81
     Wire
    0.81
     Herald
    0.81
     Gazette
    0.80
     Investigative
    0.76
    Act Density 0.082%

    No Known Activations