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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating personal preferences or favorites

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

    my favorite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.65
     للاسماء
    -0.60
    BoxShadow
    -0.58
     ISNI
    -0.57
     DMX
    -0.56
    ChildScrollView
    -0.56
     rudder
    -0.56
     Dams
    -0.55
     endblock
    -0.54
    了嗎
    -0.54
    POSITIVE LOGITS
     favorite
    1.91
    favorite
    1.74
     Favorite
    1.69
    Favorite
    1.64
     favourite
    1.63
     FAVORITE
    1.57
    favourite
    1.42
     Favourite
    1.39
     favorites
    1.29
     favorit
    1.27
    Act Density 0.003%

    No Known Activations