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

    Neuronpedia

    INDEX
    Explanations

    news-related terms or headlines

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Azerb
    -0.63
    pex
    -0.62
     Gaw
    -0.58
    iour
    -0.56
    chal
    -0.56
    gling
    -0.55
    oufl
    -0.54
    gat
    -0.54
    innon
    -0.53
     artificially
    -0.53
    POSITIVE LOGITS
     Transcript
    0.93
     Quote
    0.88
     âĢº
    0.85
     ·
    0.85
     Featured
    0.84
     âĸº
    0.80
     Joined
    0.80
     Published
    0.79
     Posted
    0.78
     Please
    0.77
    Act Density 0.280%

    No Known Activations