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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    excerpts or segments of dialogue from interviews or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reserve
    -0.70
    etheless
    -0.68
     betting
    -0.68
     cavalry
    -0.67
     reck
    -0.67
     decoration
    -0.65
     Derby
    -0.65
     lifes
    -0.65
     brigade
    -0.64
     insured
    -0.63
    POSITIVE LOGITS
    Interview
    1.59
    Question
    1.34
    VICE
    1.28
    Asked
    1.17
    Listen
    1.12
    Hello
    1.09
    AUD
    1.07
    Opening
    1.02
    Guest
    1.02
    Hi
    1.01
    Act Density 0.315%

    No Known Activations