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

    Neuronpedia

    INDEX
    Explanations

    references to favorite or preferred items

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

    Follows "favorite"

    np_acts-logits-general · gemini-2.0-flash

    favorite things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    modelBuilder
    -0.79
     $_(
    -0.65
    XMLSchema
    -0.65
    ImageContext
    -0.64
    Autoritní
    -0.63
     للاسماء
    -0.61
    makeConstraints
    -0.60
     ſind
    -0.59
     CGSize
    -0.58
     hulls
    -0.58
    POSITIVE LOGITS
     favorite
    1.09
     favourite
    1.06
    favorite
    1.05
    Favorite
    1.05
     Favorite
    1.02
     Favourite
    0.96
    favourite
    0.94
     FAVORITE
    0.92
    Favourite
    0.92
     favorites
    0.85
    Act Density 0.064%

    No Known Activations