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

    Neuronpedia

    INDEX
    Explanations

    items related to programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rigue
    -0.55
     enfans
    -0.51
     épaules
    -0.50
     lèvres
    -0.48
     vérit
    -0.44
     prêtres
    -0.43
     âmes
    -0.43
     boî
    -0.43
     vœux
    -0.42
     inconvénients
    -0.42
    POSITIVE LOGITS
     layouts
    1.00
    patches
    0.98
     sauces
    0.97
     races
    0.96
     grids
    0.96
     patches
    0.95
     nests
    0.95
     routes
    0.95
    boxes
    0.95
    sessions
    0.94
    Act Density 7.409%

    No Known Activations