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

    Neuronpedia

    INDEX
    Explanations

    various forms of textual quotes in the document

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

    phrases introducing quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     M
    -0.52
     Rens
    -0.48
     H
    -0.46
     B
    -0.46
     HM
    -0.45
     S
    -0.45
    -
    -0.45
     (
    -0.44
     Ens
    -0.44
     BM
    -0.44
    POSITIVE LOGITS
     Quote
    1.13
     QUOTE
    1.10
    Quote
    1.08
     quote
    1.02
    quote
    1.01
    Quotation
    0.92
     Quo
    0.91
     quotes
    0.89
     quoting
    0.88
     Quotes
    0.86
    Act Density 0.008%

    No Known Activations