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

    Neuronpedia

    INDEX
    Explanations

    mathematical citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ávÄĽ
    -0.19
    DITION
    -0.15
    bek
    -0.15
    .defer
    -0.15
    еÑĦ
    -0.14
    okens
    -0.14
    _ENSURE
    -0.14
    odox
    -0.14
    ycz
    -0.13
    .om
    -0.13
    POSITIVE LOGITS
    .Scroll
    0.15
     guar
    0.15
    Scroll
    0.14
    åĢĴ
    0.14
     Kushner
    0.13
    ls
    0.13
    kers
    0.13
    anst
    0.13
     xx
    0.13
     eb
    0.13
    Act Density 0.011%

    No Known Activations