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

    Neuronpedia

    INDEX
    Explanations

    instances of quotes and citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spett
    -0.66
    sem
    -0.61
     [{
    -0.60
     Drury
    -0.59
    ness
    -0.59
     III
    -0.58
    Mar
    -0.58
     Ba
    -0.57
    De
    -0.57
    vestre
    -0.57
    POSITIVE LOGITS
     quote
    2.52
     quotes
    2.38
     Quote
    2.38
    quote
    2.35
    Quote
    2.31
     QUOTE
    2.15
    quotes
    2.12
    Quotes
    2.09
     quoting
    2.03
     Quotes
    2.01
    Act Density 0.053%

    No Known Activations