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

    Neuronpedia

    INDEX
    Explanations

    references to the future and its implications

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

    "Future"

    np_acts-logits-general · gemini-2.0-flash

    future wise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cardigan
    -0.48
    txtName
    -0.47
    eba
    -0.47
    nál
    -0.47
    Affirmed
    -0.46
    mişti
    -0.46
     cardigan
    -0.45
    "}";
    -0.45
     omge
    -0.45
    ologico
    -0.45
    POSITIVE LOGITS
     generations
    1.06
     tense
    0.94
    proofing
    0.91
     proofing
    0.83
    proof
    0.83
     Tense
    0.83
     prospects
    0.82
    FUTURE
    0.78
    ukunft
    0.72
    WebVitals
    0.72
    Act Density 0.086%

    No Known Activations