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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of locations and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.15
    hound
    -0.14
    ;if
    -0.14
    iddi
    -0.14
    ÐŁÐļ
    -0.14
    .Dto
    -0.13
    –and
    -0.13
    hiba
    -0.13
    etler
    -0.13
    alley
    -0.13
    POSITIVE LOGITS
    ville
    0.23
    sville
    0.23
    erville
    0.20
     Junction
    0.19
     Hague
    0.19
    -town
    0.19
    ington
    0.18
    sburg
    0.18
    apolis
    0.18
    adelphia
    0.17
    Act Density 0.536%

    No Known Activations