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

    Neuronpedia

    INDEX
    Explanations

    quotations or phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.87
    ichick
    -0.83
    gart
    -0.81
    estate
    -0.75
    appers
    -0.72
    adh
    -0.72
    icz
    -0.72
    ipeg
    -0.71
    ibaba
    -0.69
    ntil
    -0.68
    POSITIVE LOGITS
     quote
    1.09
     quotes
    1.06
     quotation
    0.87
     quoting
    0.86
     phrases
    0.86
     quoted
    0.82
     quotations
    0.81
     attributed
    0.80
     excerpts
    0.78
    phrase
    0.77
    Act Density 0.022%

    No Known Activations