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

    Neuronpedia

    INDEX
    Explanations

    salutations and personalized messages in a written communication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'S' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},"
    -0.78
    urated
    -0.68
    aden
    -0.68
    artments
    -0.67
    ĸļ
    -0.67
    elled
    -0.66
    window
    -0.65
    ãĥı
    -0.65
    resolution
    -0.65
    Catalog
    -0.63
    POSITIVE LOGITS
     disclaimer
    1.01
     note
    0.92
     aside
    0.91
     caveat
    0.85
    Disclaimer
    0.79
     caveats
    0.78
     NOTE
    0.78
    :]
    0.78
     icing
    0.75
     obligatory
    0.75
    Act Density 0.318%

    No Known Activations