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

    Neuronpedia

    INDEX
    Explanations

    punctuations, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.94
     Савезне
    -0.89
    TagMode
    -0.87
     Мексичка
    -0.85
     становника
    -0.84
     فريبيس
    -0.84
    NameInMap
    -0.84
     ſta
    -0.83
    хьтан
    -0.83
     חיצוניים
    -0.82
    POSITIVE LOGITS
     
    0.59
    -
    0.59
    :
    0.57
    cor
    0.53
     :
    0.48
    …
    0.48
    ha
    0.48
    cin
    0.48
    ‌
    0.48
     tay
    0.47
    Act Density 0.390%

    No Known Activations