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

    Neuronpedia

    INDEX
    Explanations

    specific expressions of disappointment or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.76
     للاسماء
    -0.59
     оригіналу
    -0.52
     Anſ
    -0.46
     utafitiHapana
    -0.43
    KommentareTeilen
    -0.41
     StatefulWidget
    -0.40
     ſever
    -0.39
    таратура
    -0.39
    ſelves
    -0.37
    POSITIVE LOGITS
     blogging
    0.59
     Blogging
    0.58
    Blog
    0.58
     BLOG
    0.57
     blog
    0.57
    BLOG
    0.56
    blog
    0.55
    
    0.54
     Blog
    0.53
     blogs
    0.50
    Act Density 0.919%

    No Known Activations