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

    Neuronpedia

    INDEX
    Explanations

    language that expresses urgency and seriousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    653
    -0.16
     Sears
    -0.15
    374
    -0.15
     Kindle
    -0.15
     growth
    -0.14
    wire
    -0.13
    830
    -0.13
    kes
    -0.13
    834
    -0.13
    earn
    -0.13
    POSITIVE LOGITS
    çħ§
    0.21
    orer
    0.16
    avax
    0.16
     Danger
    0.15
    orris
    0.15
     ìĶ¨
    0.14
    mares
    0.14
    adam
    0.14
    bnb
    0.14
    ikt
    0.14
    Act Density 0.019%

    No Known Activations