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

    Neuronpedia

    INDEX
    Explanations

    references to legal or official documentation and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĹĦ
    -0.14
    ekl
    -0.14
    íį¼
    -0.14
    sters
    -0.14
    ÑĪки
    -0.14
    ãģĵãģĨ
    -0.14
    ATS
    -0.14
    ëĬĶì§Ģ
    -0.14
    iry
    -0.14
    enk
    -0.13
    POSITIVE LOGITS
     ie
    0.69
     i
    0.62
     meaning
    0.56
     ÛĮعÙĨÛĮ
    0.56
     ì¦ī
    0.54
     yani
    0.52
     ÑĤобÑĤо
    0.50
    ie
    0.49
    meaning
    0.48
     Meaning
    0.47
    Act Density 0.581%

    No Known Activations