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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and architectural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.56
     oignons
    -0.56
    stretchr
    -0.54
    Datuak
    -0.51
     drep
    -0.50
    aarrggbb
    -0.47
     oeufs
    -0.47
    WebControls
    -0.47
    AlterField
    -0.46
    lit
    -0.44
    POSITIVE LOGITS
     extracts
    0.97
     Extracts
    0.94
     extract
    0.89
     Landscape
    0.83
     flour
    0.81
     Extract
    0.80
    SharedCtor
    0.77
     LANDSCAPE
    0.76
    Flour
    0.76
    extract
    0.75
    Act Density 0.084%

    No Known Activations