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

    Neuronpedia

    INDEX
    Explanations

    emphasis on comparative phrases indicating increase or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ***!
    -0.73
    󠁢
    -0.71
    asgi
    -0.70
    pylab
    -0.68
    AnchorStyles
    -0.67
     myſelf
    -0.65
    ValueGenerated
    -0.63
     Вікіпе
    -0.63
     للمعارف
    -0.63
     ویکی‌پدی
    -0.61
    POSITIVE LOGITS
     further
    0.80
    further
    0.75
     FURTHER
    0.74
    Further
    0.69
     Further
    0.68
    FURTHER
    0.66
    进一步
    0.60
     deeper
    0.58
     deepening
    0.56
     deepen
    0.55
    Act Density 0.182%

    No Known Activations