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

    Neuronpedia

    INDEX
    Explanations

    mentions of the honorific "Mr." followed by a person's name

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or titles that start with "Mr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -1.04
     destro
    -0.91
    bley
    -0.87
    wcs
    -0.85
    quartered
    -0.79
    obyl
    -0.79
     unden
    -0.78
     condem
    -0.75
    ebook
    -0.74
     livest
    -0.73
    POSITIVE LOGITS
     Robot
    1.06
     Claus
    1.04
     Olympia
    1.02
     Hyde
    0.98
     Universe
    0.92
     Spock
    0.91
     Weasley
    0.88
     Potato
    0.85
     Rogers
    0.84
     Satan
    0.84
    Act Density 0.034%

    No Known Activations