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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and statistics related to human factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     baģlantılar
    -0.19
    ÄįÃŃ
    -0.17
     Onun
    -0.17
    ranÃŃ
    -0.17
     Bölüm
    -0.17
     Nasıl
    -0.17
     DeÄŁer
    -0.17
     pylint
    -0.17
     VÅ¡ech
    -0.16
    cé
    -0.16
    POSITIVE LOGITS
     kazan
    0.19
     TOK
    0.19
     Cay
    0.18
     Nev
    0.18
     Bey
    0.17
     Kah
    0.17
     Kay
    0.17
     Batman
    0.17
    ;
    0.17
    ALES
    0.16
    Act Density 0.050%

    No Known Activations