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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate absolutes or strong negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auffi
    -0.69
     theils
    -0.67
     faſt
    -0.64
     itſelf
    -0.62
     Theſe
    -0.61
     prefi
    -0.60
    </caption>
    -0.60
     ainfi
    -0.60
     ſtill
    -0.59
     Pompeii
    -0.59
    POSITIVE LOGITS
     keinerlei
    0.92
     InputDecoration
    0.92
     whatsoever
    0.88
     aucune
    0.79
     ویکی‌پدی
    0.67
     aucun
    0.64
     ZERO
    0.64
    毫不
    0.63
     никаких
    0.62
     никакого
    0.61
    Act Density 0.327%

    No Known Activations