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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions and publications

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.83
    cius
    -0.80
     footing
    -0.74
    ecause
    -0.73
     citiz
    -0.70
     proport
    -0.70
    cffff
    -0.69
    hement
    -0.69
    senal
    -0.66
     dictated
    -0.65
    POSITIVE LOGITS
    ↵
    0.74
    âĵĺ
    0.73
    ³³³
    0.67
    Catalog
    0.65
    à¦
    0.64
    idable
    0.63
    Els
    0.63
    Chel
    0.62
    Episode
    0.62
    Jake
    0.61
    Act Density 0.271%

    No Known Activations