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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Des."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AO
    -0.16
     subtly
    -0.16
    orsche
    -0.16
    üçük
    -0.15
    kea
    -0.15
    wap
    -0.15
    lobs
    -0.15
    -ci
    -0.14
    zsche
    -0.14
    ioneer
    -0.14
    POSITIVE LOGITS
    DED
    0.18
    574
    0.15
    AGMA
    0.15
    779
    0.15
    iy
    0.14
     Riley
    0.14
    ey
    0.14
    674
    0.14
     Bris
    0.13
     fight
    0.13
    Act Density 0.021%

    No Known Activations