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

    Neuronpedia

    INDEX
    Explanations

    data related to research studies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    halla
    -0.94
    oÄŁ
    -0.91
    omnia
    -0.89
     Brav
    -0.86
    âĹ¼
    -0.85
    Draft
    -0.84
     Origins
    -0.84
    DK
    -0.84
     Advis
    -0.83
     Events
    -0.82
    POSITIVE LOGITS
     than
    1.70
    ened
    1.37
    ening
    1.17
     forgiving
    1.17
     stringent
    1.07
    than
    1.03
     conspicuous
    1.01
     manageable
    1.01
     fortunate
    1.00
     Than
    1.00
    Act Density 0.918%

    No Known Activations