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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of places and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etler
    -0.18
    iddi
    -0.15
    oner
    -0.14
    mür
    -0.14
     Rooney
    -0.14
    –and
    -0.14
    uard
    -0.13
    lies
    -0.13
    ierge
    -0.13
    ozor
    -0.13
    POSITIVE LOGITS
    sville
    0.26
    neapolis
    0.26
    apolis
    0.26
    ville
    0.25
    åı¤å±ĭ
    0.25
     Hague
    0.24
    stown
    0.24
    adelphia
    0.24
    -town
    0.22
    zhou
    0.22
    Act Density 0.585%

    No Known Activations