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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in lists or outlining steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.85
     estimés
    -0.82
    脚注の使い方
    -0.78
     للمعارف
    -0.75
     Савезне
    -0.74
    +#+#
    -0.69
    ORAGE
    -0.65
     BitmapFactory
    -0.63
     насељу
    -0.62
     Приступљено
    -0.62
    POSITIVE LOGITS
    ↵↵
    1.30
    ↵
    1.10
    ↵↵↵
    1.03
    ↵↵↵↵
    0.98
    <eos>
    0.93
    ↵↵↵↵↵
    0.86
    ↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵↵↵↵
    0.70
    Act Density 0.391%

    No Known Activations