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

    Neuronpedia

    INDEX
    Explanations

    direct quotes or paraphrases from individuals expressing opinions or statements

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

    Quotation marks followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    said attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -1.08
    RectangleBorder
    -1.05
    ंदीखरीदारी
    -0.99
     CreateTagHelper
    -0.99
     ویکی‌پدیا
    -0.97
     nahilalakip
    -0.93
     EconPapers
    -0.93
    TestingModule
    -0.91
     препратки
    -0.89
     AssemblyCulture
    -0.88
    POSITIVE LOGITS
     said
    0.73
     “
    0.59
     her
    0.56
    ,
    0.56
     "
    0.54
     she
    0.54
    .
    0.54
     Mr
    0.53
    ↵↵
    0.53
    Mr
    0.52
    Act Density 0.919%

    No Known Activations