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

    Neuronpedia

    INDEX
    Explanations

    instances of quotations or references to other works or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ENS
    -0.39
     Xavier
    -0.38
     CEM
    -0.38
     Carey
    -0.38
    Xavier
    -0.37
     Eber
    -0.36
     Beres
    -0.36
    [#
    -0.35
     Glover
    -0.35
    warm
    -0.35
    POSITIVE LOGITS
     quote
    1.91
     quoting
    1.72
     quoted
    1.72
     quotes
    1.70
    Quote
    1.65
    quote
    1.65
     Quote
    1.56
     QUOTE
    1.55
     quotation
    1.51
     quotations
    1.49
    Act Density 0.330%

    No Known Activations