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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data points and statistics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exorc
    -0.74
     pleas
    -0.74
    zech
    -0.70
    ê
    -0.69
     charms
    -0.68
     charm
    -0.68
    uve
    -0.66
     prayers
    -0.66
     cann
    -0.66
     commun
    -0.64
    POSITIVE LOGITS
     dataset
    1.42
    verages
    1.41
     graphs
    1.31
     statistical
    1.26
     averages
    1.25
     spreadsheet
    1.24
     datasets
    1.21
    efficients
    1.18
     methodology
    1.15
     weighted
    1.11
    Act Density 1.001%

    No Known Activations