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

    Neuronpedia

    INDEX
    Explanations

    references to old versus new concepts, particularly in the context of societal change

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

    old world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.41
    CppMethod
    -0.36
     propOrder
    -0.30
     säll
    -0.29
     tils
    -0.27
    ęp
    -0.27
    ByUrl
    -0.27
     nakalista
    -0.27
    でしょう
    -0.27
     Vortrag
    -0.26
    POSITIVE LOGITS
     old
    0.99
    旧
    0.97
    舊
    0.95
     Old
    0.90
     旧
    0.89
    old
    0.88
    Old
    0.87
     régi
    0.85
     vecchio
    0.84
     vecchi
    0.84
    Act Density 0.121%

    No Known Activations