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

    Neuronpedia

    INDEX
    Explanations

    structured references to weekly summaries or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sho
    -0.18
     sym
    -0.16
     shel
    -0.14
    izzer
    -0.14
     Sym
    -0.14
    .glob
    -0.14
    enk
    -0.13
    Sym
    -0.13
    iti
    -0.13
    /**<
    -0.13
    POSITIVE LOGITS
     week
    0.17
    _Items
    0.17
    Segments
    0.14
     weekly
    0.14
    HeaderValue
    0.14
     Week
    0.14
    OfWeek
    0.14
    íĥķ
    0.13
     çī
    0.13
    akh
    0.13
    Act Density 0.068%

    No Known Activations