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

    Neuronpedia

    INDEX
    Explanations

    terms related to scams and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Mapping
    -0.16
    :animated
    -0.15
    implify
    -0.15
    imeline
    -0.15
    askell
    -0.14
    ãĥ¼ãĥĹ
    -0.14
    twig
    -0.14
    wand
    -0.14
    essed
    -0.14
    lee
    -0.13
    POSITIVE LOGITS
    sters
    0.18
    666
    0.14
    /mock
    0.14
     Stap
    0.14
    à¥Īय
    0.14
    adoo
    0.14
     spit
    0.14
    ewis
    0.14
    238
    0.14
    ub
    0.14
    Act Density 0.013%

    No Known Activations