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

    Neuronpedia

    INDEX
    Explanations

    mentions of libraries

    oai_token-act-pair · gpt-3.5-turbo

    references to libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dak
    -0.73
     ¯
    -0.72
    votes
    -0.66
     Guinea
    -0.66
    etically
    -0.65
    ente
    -0.65
     Zeal
    -0.64
    placed
    -0.64
    acted
    -0.63
     Chero
    -0.62
    POSITIVE LOGITS
     library
    3.77
     libraries
    3.03
     Library
    2.86
     Libraries
    2.58
    Library
    2.23
    library
    2.19
    ibraries
    1.78
     bookstore
    1.60
    ibrarian
    1.50
    ibrary
    1.45
    Act Density 0.011%

    No Known Activations