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

    Neuronpedia

    INDEX
    Explanations

    specific numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to dates or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.87
    achus
    -0.80
    rous
    -0.79
    eton
    -0.76
    aye
    -0.74
    eners
    -0.74
    achu
    -0.72
    orthy
    -0.68
    igham
    -0.67
    atoon
    -0.67
    POSITIVE LOGITS
    20439
    1.05
    teen
    0.83
    th
    0.78
    teenth
    0.76
    worthiness
    0.72
    ïve
    0.70
    384
    0.70
    MHz
    0.69
    lig
    0.69
    chester
    0.68
    Act Density 0.111%

    No Known Activations