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

    Neuronpedia

    INDEX
    Explanations

    references to personal preferences or favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.65
    AddTagHelper
    -0.57
    ed
    -0.54
    en
    -0.53
    ra
    -0.53
     chitarra
    -0.52
    de
    -0.52
    pr
    -0.52
     dudas
    -0.51
     in
    -0.50
    POSITIVE LOGITS
     favorite
    3.76
     favourite
    3.60
    favorite
    3.23
     Favorite
    3.19
    favourite
    3.11
     favorites
    3.07
     FAVORITE
    3.01
     Favourite
    3.00
    Favorite
    2.92
     favourites
    2.88
    Act Density 0.063%

    No Known Activations