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

    Neuronpedia

    INDEX
    Explanations

    terms related to choice and preference in products and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.09
    3:0.17
    4:0.03
    5:0.07
    6:0.03
    7:0.07
    8:0.04
    9:0.03
    10:0.28
    11:0.03
    Negative Logits
     favorites
    -2.92
     pick
    -2.68
     whenever
    -2.67
     cheaper
    -2.59
     whichever
    -2.54
     quicker
    -2.54
     favourites
    -2.43
     onto
    -2.40
     wherever
    -2.38
     favored
    -2.37
    POSITIVE LOGITS
    teness
    2.32
     millenn
    2.07
    cedented
    2.07
    ODUCT
    2.06
    ensable
    2.05
    imeo
    1.99
    REF
    1.97
    lvl
    1.95
    ANI
    1.94
    interrupted
    1.91
    Act Density 0.001%

    No Known Activations