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

    Neuronpedia

    INDEX
    Explanations

    people's names, titles, and locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with various individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Abstract
    -0.70
     isEnabled
    -0.66
    ãĥ¬
    -0.64
    ween
    -0.64
    Course
    -0.64
    Quantity
    -0.63
    ãĥ´ãĤ¡
    -0.63
    $.
    -0.62
    Sov
    -0.61
    7601
    -0.60
    POSITIVE LOGITS
     meanwhile
    1.67
     echoed
    1.32
     reacted
    1.21
     applauded
    1.17
     likewise
    1.15
     congratulated
    1.14
     intervened
    1.09
     tweeted
    1.09
     disagreed
    1.07
     also
    1.07
    Act Density 0.721%

    No Known Activations