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

    Neuronpedia

    INDEX
    Explanations

    data visualizations like charts and graphs

    oai_token-act-pair · gpt-3.5-turbo

    data related to charts and figures in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     breathed
    -0.67
     nurt
    -0.67
     Bapt
    -0.65
    vo
    -0.65
    anism
    -0.65
    assion
    -0.65
    edi
    -0.64
    anke
    -0.64
    spirit
    -0.63
     charism
    -0.63
    POSITIVE LOGITS
     graphs
    1.08
     graph
    0.99
     chart
    0.97
     computed
    0.94
     statistical
    0.94
     spreadsheet
    0.91
    verages
    0.88
     dataset
    0.87
     charts
    0.87
     Table
    0.86
    Act Density 0.799%

    No Known Activations