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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "paper" in various contexts

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

    in this paper we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.79
     Италијани
    -0.71
     '\\;'
    -0.70
    sizeCache
    -0.60
     Roskov
    -0.58
     autorytatywna
    -0.58
    Personensuche
    -0.57
     Paglinawan
    -0.57
    saraba
    -0.55
     Numerade
    -0.53
    POSITIVE LOGITS
     paper
    1.12
    paper
    0.83
     papers
    0.74
     article
    0.69
    Paper
    0.67
     Paper
    0.66
     papier
    0.65
     kertas
    0.64
     articles
    0.64
     PAPER
    0.64
    Act Density 0.018%

    No Known Activations