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

    Neuronpedia

    INDEX
    Explanations

    paragraph markers or structural elements indicating the beginning of a new section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.88
    ніципа
    -0.87
    ⓧ
    -0.84
     Савезне
    -0.82
     nahilalakip
    -0.80
     سكانية
    -0.79
    ########.
    -0.76
    ьаж
    -0.75
     Италијани
    -0.72
     通販
    -0.71
    POSITIVE LOGITS
    userdetails
    0.47
    ↵↵
    0.47
    DBNull
    0.44
     vaih
    0.42
     Yes
    0.40
     nope
    0.39
    No
    0.39
     no
    0.39
    Yes
    0.39
    </th>
    0.38
    Act Density 0.098%

    No Known Activations