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

    Neuronpedia

    INDEX
    Explanations

    references to the term "paper."

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

    referring to the paper itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.57
    ValueGeneration
    -0.41
     Վերցված
    -0.39
    abet
    -0.39
    Халык
    -0.39
    TRAILING
    -0.38
    phorus
    -0.37
    MergeFrom
    -0.36
    omni
    -0.36
    Controllo
    -0.35
    POSITIVE LOGITS
     paper
    1.41
     papers
    1.27
     Papers
    1.13
     Paper
    1.13
     PAPER
    1.08
     PAPERS
    1.02
    Paper
    1.02
    Papers
    1.00
    paper
    0.97
    papers
    0.96
    Act Density 0.017%

    No Known Activations