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

    Neuronpedia

    INDEX
    Explanations

    location-based phrases, particularly U.S. and Canadian place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensch
    -0.15
    }elseif
    -0.15
    noon
    -0.15
    ÙĪغ
    -0.14
    stein
    -0.14
    ized
    -0.14
    elez
    -0.14
    baugh
    -0.14
    elli
    -0.14
    olkien
    -0.14
    POSITIVE LOGITS
    orida
    0.18
    inois
    0.17
    lahoma
    0.16
     USA
    0.15
    CompanyName
    0.15
     Jah
    0.15
    io
    0.15
    ptal
    0.15
     area
    0.15
    -area
    0.14
    Act Density 0.072%

    No Known Activations