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

    Neuronpedia

    INDEX
    Explanations

    opening and closing brackets or braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.60
    <bos>
    -0.58
    '
    -0.58
     
    -0.57
    ↵↵
    -0.57
    ↵↵↵
    -0.51
    何より
    -0.50
    ↵↵↵↵
    -0.47
    <h3>
    -0.47
    ...
    -0.46
    POSITIVE LOGITS
    下载附件
    0.99
    Билгалдахарш
    0.99
    hoeddwyd
    0.91
     Normdatei
    0.91
    rawDesc
    0.89
     صوتيه
    0.85
     pinulongan
    0.85
    Geplaatst
    0.83
    awaiter
    0.82
    تقاوى
    0.82
    Act Density 0.101%

    No Known Activations