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

    Neuronpedia

    INDEX
    Explanations

    references and citations within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Russo
    -0.16
     Ru
    -0.15
     dirt
    -0.14
    ander
    -0.14
    igu
    -0.14
     Dirt
    -0.14
     beg
    -0.14
    ought
    -0.13
    ,
    -0.13
    ickle
    -0.13
    POSITIVE LOGITS
    oref
    0.15
    pez
    0.15
    illac
    0.15
    ÑĸзнеÑģ
    0.15
     BaseService
    0.14
    ÙĨدا
    0.14
    otas
    0.14
    ży
    0.14
    âĢĮÙĨ
    0.14
    ottes
    0.14
    Act Density 0.011%

    No Known Activations