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

    Neuronpedia

    INDEX
    Explanations

    references to the Victorian era

    oai_token-act-pair · gpt-3.5-turbo

    references to the Victorian era and the word "Victorian" itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arenthood
    -0.86
    earance
    -0.82
    unin
    -0.82
    lopp
    -0.80
    chery
    -0.80
    swers
    -0.79
    cific
    -0.79
    etically
    -0.79
    ration
    -0.78
    akening
    -0.78
    POSITIVE LOGITS
     Sparkle
    1.07
     Actress
    0.77
    BuyableInstoreAndOnline
    0.77
     Railway
    0.77
     Nadu
    0.73
     Tigers
    0.73
     Era
    0.72
     Gothic
    0.70
     Violet
    0.70
     Optical
    0.68
    Act Density 0.044%

    No Known Activations