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

    Neuronpedia

    INDEX
    Explanations

    random characters and words that appear to have no clear relation to a specific pattern or theme

    oai_token-act-pair · gpt-3.5-turbo

    specific formatting or notation styles used in numerical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.69
    ritic
    -0.69
    aceutical
    -0.68
     sucker
    -0.67
    stitial
    -0.65
    ydia
    -0.64
    nces
    -0.64
    rod
    -0.64
    cki
    -0.64
    punk
    -0.63
    POSITIVE LOGITS
     ÃĹ
    1.12
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.03
    âĢ¢âĢ¢
    0.92
    ++++++++++++++++
    0.78
    ++++++++
    0.74
    _>
    0.74
    -+-+
    0.72
    ··
    0.69
    ï¸
    0.67
    ÃĹ
    0.65
    Act Density 0.009%

    No Known Activations