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

    Neuronpedia

    INDEX
    Explanations

    references to sources and attributions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bach
    -0.14
     fro
    -0.13
     PQ
    -0.13
    ức
    -0.13
    inz
    -0.13
     Sor
    -0.13
     backpack
    -0.13
     Flesh
    -0.13
     Burning
    -0.13
    XXX
    -0.13
    POSITIVE LOGITS
    utterstock
    0.15
    ornings
    0.15
    еÑĢÑĤи
    0.15
    opia
    0.14
    atrice
    0.14
    Courtesy
    0.14
    اÛĮØ´
    0.14
    submenu
    0.14
    .gdx
    0.13
     Kons
    0.13
    Act Density 0.051%

    No Known Activations