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

    Neuronpedia

    INDEX
    Explanations

    quotes or references mentioned within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.73
    adh
    -0.72
    axies
    -0.70
    ggles
    -0.70
    gart
    -0.70
    appers
    -0.69
    izen
    -0.68
    ichick
    -0.67
    estate
    -0.67
     Drift
    -0.66
    POSITIVE LOGITS
     quote
    1.10
     quotes
    1.07
     quoting
    0.92
     quotation
    0.88
     phrases
    0.87
     quotations
    0.83
     quoted
    0.80
     wording
    0.79
     attributed
    0.77
     uttered
    0.76
    Act Density 0.016%

    No Known Activations