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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data points in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or values commonly associated with lists or references in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyd
    -0.85
    atem
    -0.85
    ogue
    -0.74
    ation
    -0.70
    ãĤ¡
    -0.68
     Beckham
    -0.67
    igating
    -0.67
    omial
    -0.67
    atives
    -0.66
    nih
    -0.66
    POSITIVE LOGITS
    teenth
    0.93
    393
    0.92
    08
    0.89
    06
    0.89
    th
    0.88
    07
    0.86
    09
    0.85
    92
    0.84
    03
    0.84
    05
    0.84
    Act Density 0.038%

    No Known Activations