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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    bootstrapcdn
    -0.62
     betweenstory
    -0.59
    BorderFactory
    -0.55
    carpa
    -0.52
    JScrollPane
    -0.51
     ویکی‌پدیا
    -0.50
    Παραπομπές
    -0.50
    Kjelder
    -0.49
    styleType
    -0.47
    POSITIVE LOGITS
     but
    3.35
     But
    2.66
    but
    2.64
     entanto
    2.64
    But
    2.60
     pero
    2.56
     nhưng
    2.54
     tetapi
    2.51
     However
    2.50
     however
    2.50
    Act Density 0.699%

    No Known Activations