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

    Neuronpedia

    INDEX
    Explanations

    words related to geographic locations, especially cities and regions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that include a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´
    -0.73
    =-=-=-=-=-=-=-=-
    -0.70
     transact
    -0.67
    ļéĨĴ
    -0.65
     paranormal
    -0.62
     rhy
    -0.61
     improper
    -0.61
    ibles
    -0.61
     retrospective
    -0.60
     dictate
    -0.60
    POSITIVE LOGITS
     Columb
    0.81
    Va
    0.76
     Rivers
    0.73
     Petersburg
    0.73
     Sabb
    0.70
     Huss
    0.69
     Mub
    0.67
    interstitial
    0.65
     York
    0.65
     Eliot
    0.65
    Act Density 0.042%

    No Known Activations