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

    Neuronpedia

    INDEX
    Explanations

    references to formatting functions and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estimés
    -0.78
    равда
    -0.75
     Moreau
    -0.70
    AsUp
    -0.69
    انجليز
    -0.69
     industriale
    -0.68
     popoli
    -0.68
     meshes
    -0.68
    #+#
    -0.67
    Geplaatst
    -0.67
    POSITIVE LOGITS
    formatter
    1.45
    Formatter
    1.45
     formatter
    1.41
    DateFormatter
    0.80
     Gazetteer
    0.78
    Приятного
    0.73
    BibitemShut
    0.69
     tà
    0.69
     Uniti
    0.66
     Barbar
    0.66
    Act Density 0.003%

    No Known Activations