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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ä°nsan
    -0.20
     Bölüm
    -0.18
     baģlantılar
    -0.18
     DÃ¼ÅŁ
    -0.18
     Åŀu
    -0.17
     Bütün
    -0.17
     KiÅŁ
    -0.17
     MÃ¼ÅŁ
    -0.17
     Düny
    -0.17
     Bazı
    -0.16
    POSITIVE LOGITS
     Sey
    0.20
     TOK
    0.19
     Bey
    0.18
     ı
    0.18
    ̧
    0.17
     Cay
    0.17
     Pam
    0.17
     Bir
    0.16
     Erd
    0.15
    .dep
    0.15
    Act Density 0.074%

    No Known Activations