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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulation and standards in various fields

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manip
    -0.68
     squared
    -0.68
     rob
    -0.66
    heit
    -0.66
    Bey
    -0.65
     Breaker
    -0.65
     Ramos
    -0.64
     Fernand
    -0.64
    owler
    -0.62
     Swed
    -0.61
    POSITIVE LOGITS
    uit
    1.25
    uits
    1.25
    hip
    1.13
    ibilities
    0.95
    ury
    0.93
    ensical
    0.93
    ĸļ
    0.92
    chwitz
    0.92
    uries
    0.88
    rences
    0.87
    Act Density 0.020%

    No Known Activations