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

    Neuronpedia

    INDEX
    Explanations

    titles of nobility

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the title "Lord."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.77
    uters
    -0.72
    aneously
    -0.71
    urses
    -0.69
    akura
    -0.68
    illus
    -0.67
    utic
    -0.67
    ¥ŀ
    -0.66
    atinum
    -0.66
    given
    -0.66
    POSITIVE LOGITS
     Vader
    0.89
     Voldemort
    0.89
    bridge
    0.88
    stown
    0.86
     Byron
    0.85
     Shiva
    0.82
     Sandwich
    0.82
     Trafford
    0.81
     Chester
    0.81
    aer
    0.80
    Act Density 0.032%

    No Known Activations