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

    Neuronpedia

    INDEX
    Explanations

    concepts related to criticism and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yr
    -0.17
    aurant
    -0.16
    ted
    -0.16
    ÏħÏĩ
    -0.15
    adge
    -0.15
     ка
    -0.14
    illery
    -0.14
    æ§
    -0.14
     integrity
    -0.14
     situ
    -0.14
    POSITIVE LOGITS
    heimer
    0.17
    BOTTOM
    0.16
    ookies
    0.15
    oggler
    0.15
    kker
    0.15
    ienes
    0.15
    Descriptions
    0.15
    uba
    0.14
    æ¸Ī
    0.14
    chine
    0.14
    Act Density 0.535%

    No Known Activations