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

    Neuronpedia

    INDEX
    Explanations

    references to popular and well-known companies or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.02
    3:0.10
    4:0.04
    5:0.09
    6:0.07
    7:0.02
    8:0.38
    9:0.06
    10:0.01
    11:0.01
    Negative Logits
    sectional
    -1.76
     Constable
    -1.71
    vasive
    -1.66
    estyles
    -1.65
    fur
    -1.65
    atures
    -1.63
    opian
    -1.60
     essays
    -1.60
    ocument
    -1.59
     Beir
    -1.57
    POSITIVE LOGITS
     monopoly
    2.19
     manufactures
    2.15
     manufacturer
    2.10
     supplier
    1.99
     subsidiaries
    1.95
     owns
    1.91
     collaborate
    1.90
     owning
    1.88
     royalties
    1.87
     competitor
    1.86
    Act Density 0.575%

    No Known Activations