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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to architecture and structural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙIJÙĥ
    -0.16
    ENA
    -0.16
    ke
    -0.15
    589
    -0.15
    orris
    -0.14
     Sinn
    -0.14
    ائ
    -0.14
    ixer
    -0.14
     Kami
    -0.14
    ena
    -0.14
    POSITIVE LOGITS
    oÅĽci
    0.16
    odÃŃ
    0.16
    exas
    0.15
     Köy
    0.15
    ë¡Ģ
    0.15
    witter
    0.14
    æ·»
    0.14
    ẽ
    0.14
    istring
    0.14
    ạnh
    0.14
    Act Density 0.017%

    No Known Activations