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

    Neuronpedia

    INDEX
    Explanations

    references to 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
    ls
    -0.72
    irin
    -0.68
    empt
    -0.67
    pid
    -0.64
    vo
    -0.63
     Awakening
    -0.63
    Pacific
    -0.62
    verty
    -0.62
    awk
    -0.61
    ald
    -0.61
    POSITIVE LOGITS
     library
    0.93
    gdala
    0.90
     libraries
    0.87
    DragonMagazine
    0.85
     Libraries
    0.85
    conservancy
    0.79
    ibrary
    0.78
    Library
    0.78
    HCR
    0.78
    ĸļ
    0.77
    Act Density 0.011%

    No Known Activations