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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities or classifications of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    322
    -0.20
    ior
    -0.17
    inst
    -0.17
    329
    -0.15
    s
    -0.14
    358
    -0.14
    298
    -0.14
    oyer
    -0.14
    OH
    -0.14
    483
    -0.14
    POSITIVE LOGITS
    ltra
    0.15
    icha
    0.15
    екÑĤÑĥ
    0.14
    regor
    0.14
    ansa
    0.14
    adic
    0.14
    ekyll
    0.14
    ëģ
    0.14
    .asp
    0.14
    ãĥ¼ãĤ¹
    0.13
    Act Density 0.053%

    No Known Activations