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

    Neuronpedia

    INDEX
    Explanations

    locations or structures within buildings

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to locations and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIDIA
    -0.80
    vous
    -0.74
    Enlarge
    -0.74
    ISC
    -0.66
    Bay
    -0.65
    NetMessage
    -0.65
    >>>>
    -0.62
     Prosper
    -0.61
    paces
    -0.60
    sonian
    -0.59
    POSITIVE LOGITS
    mates
    0.98
    mate
    0.87
     layout
    0.80
    wide
    0.80
     mates
    0.74
     dwell
    0.73
     etiquette
    0.73
     layouts
    0.72
     decoration
    0.72
    side
    0.72
    Act Density 0.532%

    No Known Activations