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

    Neuronpedia

    INDEX
    Explanations

    references to academic research and dissertations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.97
    Autoritní
    -0.92
    Билгалдахарш
    -0.84
     disambiguazione
    -0.79
     AssemblyCulture
    -0.78
    Rè
    -0.77
    TestingModule
    -0.75
     <<<<<<<<<<<<<<
    -0.74
     invokingState
    -0.73
     autorytatywna
    -0.73
    POSITIVE LOGITS
     thesis
    0.46
    क्
    0.45
     personnelles
    0.41
    id
    0.41
    存在的
    0.40
     inconnu
    0.40
     xếp
    0.39
     utafiti
    0.39
     meuble
    0.39
     étrangères
    0.38
    Act Density 0.544%

    No Known Activations