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

    Neuronpedia

    INDEX
    Explanations

    references to language and multilingualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.17
    erva
    -0.16
    stal
    -0.16
    mere
    -0.15
    æĪ¸
    -0.14
    erton
    -0.14
    unch
    -0.14
    terms
    -0.14
    ç©
    -0.14
    uhan
    -0.14
    POSITIVE LOGITS
    amment
    0.16
    ofday
    0.16
    775
    0.15
    ırak
    0.14
    687
    0.14
    義
    0.14
    addir
    0.14
    SI
    0.14
    unning
    0.13
    295
    0.13
    Act Density 0.024%

    No Known Activations