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

    Neuronpedia

    INDEX
    Explanations

    concepts related to caution and potential future consequences

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

    and phrases about "future" and "near"

    np_acts-logits-general · gemini-2.0-flash

    words indicating future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    layan
    -0.47
    ModelState
    -0.46
    Erreferentziak
    -0.42
    migiano
    -0.42
    asgi
    -0.41
    ńcz
    -0.41
    runApp
    -0.41
    emia
    -0.41
    ῖν
    -0.41
    enci
    -0.40
    POSITIVE LOGITS
     future
    4.07
    future
    3.72
    Future
    3.42
     Future
    3.27
     FUTURE
    3.12
    FUTURE
    3.09
     futuro
    2.98
     Zukunft
    2.76
    avenir
    2.60
     futur
    2.58
    Act Density 0.602%

    No Known Activations