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

    Neuronpedia

    INDEX
    Explanations

    terms related to social welfare programs and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áž
    -0.15
    /embed
    -0.15
     dow
    -0.15
     resc
    -0.14
    lio
    -0.13
    iffin
    -0.13
    اÙĨÙĪÙĨ
    -0.13
    æĬŀ
    -0.13
    hex
    -0.13
     Tavern
    -0.13
    POSITIVE LOGITS
    BaseContext
    0.15
    \brief
    0.15
     Temporary
    0.15
    ilik
    0.15
     Laf
    0.14
    %D
    0.14
    γÏī
    0.14
     meteor
    0.14
    odate
    0.14
     buflen
    0.14
    Act Density 0.065%

    No Known Activations