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

    Neuronpedia

    INDEX
    Explanations

    references to ethical guidelines and institutional protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    years in the 2000s, particularly around 2010-2020. The neuron shows high activation for numbers starting with '20' followed by another digit, which corresponds to years in the early 21st century.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @yangmungi
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.75
    RenderAtEndOf
    -0.68
     متعلقه
    -0.66
    хьтан
    -0.63
     ۸
    -0.61
    بوابة
    -0.60
     ۴
    -0.60
    Personendaten
    -0.60
     ۶
    -0.60
    ंदीखरीदारी
    -0.59
    POSITIVE LOGITS
    1
    2.31
    １
    1.19
     ১
    1.09
    ১
    1.01
     १
    0.95
    ١
    0.89
     ١
    0.86
    १
    0.85
    ۱
    0.81
    𝟭
    0.76
    Act Density 7.719%

    No Known Activations