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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to news organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Norn
    -0.81
    akings
    -0.72
    worldly
    -0.69
    cific
    -0.65
    peak
    -0.65
    linked
    -0.62
    fitting
    -0.62
    Gy
    -0.61
    culated
    -0.60
    location
    -0.60
    POSITIVE LOGITS
    Truth
    0.96
     Foundation
    0.94
    ebook
    0.80
     Gazette
    0.79
     News
    0.79
    sylv
    0.78
     Publishing
    0.77
     Investigative
    0.76
    NEWS
    0.76
     Emails
    0.74
    Act Density 0.060%

    No Known Activations