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

    Neuronpedia

    INDEX
    Explanations

    references to artistic or creative work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.56
    ajevo
    -0.54
    OCITY
    -0.54
     scénario
    -0.53
    Обо
    -0.51
     conducive
    -0.51
    LookAnd
    -0.51
    vesse
    -0.49
    ʁ
    -0.49
    ígenes
    -0.48
    POSITIVE LOGITS
     work
    1.38
     trabalho
    0.90
     Arbeit
    0.87
    trabajo
    0.84
     arbeit
    0.84
     works
    0.84
     arbete
    0.83
    oredCriteria
    0.81
     работы
    0.80
     arbejde
    0.80
    Act Density 0.285%

    No Known Activations