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

    Neuronpedia

    INDEX
    Explanations

    words related to introducing or reintroducing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the introduction or reintroduction of concepts or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     luck
    -0.69
     fortune
    -0.69
     sleeper
    -0.67
     chance
    -0.62
     Europa
    -0.61
     Weinstein
    -0.60
    elf
    -0.60
     Wikimedia
    -0.59
     wage
    -0.58
     nightmare
    -0.58
    POSITIVE LOGITS
    ctory
    1.28
     Introdu
    1.18
    Introdu
    1.04
    ctions
    1.03
    pta
    1.03
    introdu
    1.00
    cci
    0.93
     introduces
    0.89
    plates
    0.86
    cing
    0.86
    Act Density 0.014%

    No Known Activations