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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CodeAt
    -0.17
    ëłī
    -0.15
    ENCHMARK
    -0.15
    PRS
    -0.14
    cie
    -0.14
    aktu
    -0.14
    eka
    -0.14
    ERA
    -0.14
    SAFE
    -0.13
    azzi
    -0.13
    POSITIVE LOGITS
    ensis
    0.17
    ån
    0.16
    ská
    0.15
     Dank
    0.14
    itable
    0.14
    ense
    0.14
    uctions
    0.13
    ensi
    0.13
    ij
    0.13
    enses
    0.13
    Act Density 0.051%

    No Known Activations