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

    Neuronpedia

    INDEX
    Explanations

    references to different public 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
    empt
    -0.65
     believer
    -0.65
    engeance
    -0.62
    natal
    -0.61
    eded
    -0.61
    pid
    -0.60
    ls
    -0.60
    charged
    -0.60
     believers
    -0.60
    ought
    -0.59
    POSITIVE LOGITS
     Library
    1.12
    Library
    0.90
    gate
    0.88
     Libraries
    0.88
    ibrary
    0.88
    ibrarian
    0.84
    HCR
    0.81
    conservancy
    0.81
    sonian
    0.80
    ystem
    0.80
    Act Density 0.008%

    No Known Activations