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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially apostrophes and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndroidJUnit
    -0.75
    :✨
    -0.73
    KURZBESCHREIBUNG
    -0.73
     ویکی‌پدیا
    -0.70
    BeginContext
    -0.67
     OFDb
    -0.66
    }">
    -0.65
    djangoproject
    -0.62
    Πηγή
    -0.61
    Liefs
    -0.61
    POSITIVE LOGITS
    ’
    0.92
    ’.
    0.58
    ’’
    0.57
    ’;
    0.54
    ’,
    0.54
    первых
    0.52
    ’-
    0.51
    ,’
    0.51
    .’
    0.51
     referrerpolicy
    0.50
    Act Density 0.215%

    No Known Activations