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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific place or location as significant or noteworthy

    oai_token-act-pair · gpt-3.5-turbo

    places or areas recognized for their significance or remoteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inexper
    -0.81
    Austral
    -0.70
    ontent
    -0.70
    intent
    -0.69
     fibers
    -0.69
     antibodies
    -0.69
     hats
    -0.69
     behaviours
    -0.68
     warranties
    -0.68
    */(
    -0.65
    POSITIVE LOGITS
     UNESCO
    1.04
     Mecca
    1.01
     hosp
    0.99
     birthplace
    0.98
     bustling
    0.98
     sanctuary
    0.97
     residential
    0.94
     inhabited
    0.94
     playground
    0.94
     farmland
    0.94
    Act Density 0.396%

    No Known Activations