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

    Neuronpedia

    INDEX
    Explanations

    words that denote geographical locations or significant proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondon
    -0.17
     Mine
    -0.15
    mine
    -0.14
     gen
    -0.14
    wu
    -0.14
    даÑı
    -0.14
    ish
    -0.13
    ilk
    -0.13
    aney
    -0.13
    lex
    -0.13
    POSITIVE LOGITS
    ëĿ½
    0.17
    ansa
    0.16
    ARRANT
    0.16
    onaut
    0.15
    orra
    0.15
    ozem
    0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.14
    elper
    0.14
     ÑĤоваÑĢи
    0.14
     ifndef
    0.14
    Act Density 0.556%

    No Known Activations