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

    Neuronpedia

    INDEX
    Explanations

    references to users and user experience-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»Ļc
    -0.15
    коÑĤ
    -0.15
    DED
    -0.15
    RelativeTo
    -0.14
    abra
    -0.14
    reed
    -0.14
    zes
    -0.14
    tat
    -0.14
    ibil
    -0.13
    actories
    -0.13
    POSITIVE LOGITS
    lings
    0.15
    ange
    0.15
    age
    0.15
    RIPT
    0.15
    \User
    0.14
    缼
    0.14
    hood
    0.14
    onus
    0.14
    whelming
    0.14
     itemprop
    0.13
    Act Density 0.051%

    No Known Activations