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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urb
    -0.15
    ield
    -0.14
    sworth
    -0.14
    359
    -0.14
    alls
    -0.14
    ederal
    -0.14
     поÑıÑģ
    -0.13
    Sdk
    -0.13
    rape
    -0.13
    aven
    -0.13
    POSITIVE LOGITS
     inheritance
    0.14
    eyin
    0.14
    ALCHEMY
    0.13
    anon
    0.13
    éļİ
    0.13
     imagin
    0.13
    anı
    0.13
     hâl
    0.13
     slowly
    0.13
    Inspectable
    0.13
    Act Density 0.057%

    No Known Activations