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

    Neuronpedia

    INDEX
    Explanations

    direct quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quoted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.71
    appers
    -0.70
    we
    -0.68
    ²¾
    -0.68
    otin
    -0.67
    cum
    -0.67
    enfranch
    -0.67
    venge
    -0.66
    gone
    -0.65
    cup
    -0.65
    POSITIVE LOGITS
     quotes
    1.23
     quoted
    1.20
     quotations
    1.03
     quoting
    1.00
     excerpts
    0.92
     quotation
    0.91
     snippets
    0.91
     phrases
    0.82
     quote
    0.82
     passages
    0.74
    Act Density 0.005%

    No Known Activations