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

    Neuronpedia

    INDEX
    Explanations

    the word "Og" and its variations, indicating a focus on a specific name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çIJ³
    -0.15
    ox
    -0.15
    adio
    -0.14
    evi
    -0.14
    ristol
    -0.14
    achel
    -0.14
    oldem
    -0.14
    ÄĽÅ¾
    -0.14
    ruit
    -0.13
    /@
    -0.13
    POSITIVE LOGITS
    óln
    0.18
    ensburg
    0.17
    igin
    0.16
     Og
    0.16
    orman
    0.16
    CreateInfo
    0.16
    :image
    0.15
    eyse
    0.15
    undler
    0.15
    ular
    0.15
    Act Density 0.009%

    No Known Activations