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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal preference or favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something is favorite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.81
     AssemblyCulture
    -0.77
     ſta
    -0.69
     Monfieur
    -0.69
    RectangleBorder
    -0.68
     Reſ
    -0.68
     Infór
    -0.65
    AddTagHelper
    -0.65
     itſelf
    -0.64
     faſt
    -0.64
    POSITIVE LOGITS
     favorite
    0.88
     favourite
    0.83
    Favorite
    0.81
     Favorite
    0.81
    favorite
    0.77
     FAVORITE
    0.75
    Favourite
    0.75
     Favourite
    0.74
    favourite
    0.72
     favorites
    0.71
    Act Density 0.008%

    No Known Activations