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

    Neuronpedia

    INDEX
    Explanations

    references to specific publications and dates

    oai_token-act-pair · gpt-3.5-turbo

    references to published works and their bibliographic details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    goal
    -0.77
    arge
    -0.77
    oooooooo
    -0.75
    omorphic
    -0.74
    root
    -0.72
    orbit
    -0.68
    ndra
    -0.67
    erm
    -0.67
    angu
    -0.67
    animate
    -0.66
    POSITIVE LOGITS
     ISBN
    1.23
     pg
    1.10
     Retrieved
    1.10
     pp
    1.08
     reprinted
    1.07
     reprint
    1.01
     Accessed
    0.95
    published
    0.93
     unpublished
    0.93
     paperback
    0.92
    Act Density 0.273%

    No Known Activations