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

    Neuronpedia

    INDEX
    Explanations

    pairs of proper nouns and surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, cities, or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ°
    -0.68
     TODAY
    -0.60
     AND
    -0.59
    benefit
    -0.58
     seiz
    -0.57
     includ
    -0.55
     WARN
    -0.54
    ItemTracker
    -0.51
     NON
    -0.51
    DonaldTrump
    -0.50
    POSITIVE LOGITS
     respectively
    1.55
     alike
    1.31
     thereof
    0.79
    depending
    0.77
     versa
    0.76
    asions
    0.67
     Halls
    0.66
     Streets
    0.65
     LLP
    0.64
     eras
    0.64
    Act Density 1.256%

    No Known Activations