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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingu
    -0.17
     Needle
    -0.14
    reen
    -0.14
    uthor
    -0.14
     pii
    -0.13
    pet
    -0.13
     Yar
    -0.13
     Maiden
    -0.13
    atori
    -0.13
    warf
    -0.13
    POSITIVE LOGITS
    -REAL
    0.14
    Ñĩенко
    0.14
    hei
    0.14
    наÑĢ
    0.14
     merak
    0.14
    ÙĪسÛĮ
    0.14
     Appropri
    0.14
    onis
    0.14
    ceipt
    0.13
    ManagerInterface
    0.13
    Act Density 0.085%

    No Known Activations