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

    Neuronpedia

    INDEX
    Explanations

    ways to introduce a shift in focus or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it turns out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.81
    aps
    -0.71
    ordan
    -0.70
    ropolitan
    -0.70
    fters
    -0.70
    icipated
    -0.69
    atana
    -0.69
    ainers
    -0.65
    capacity
    -0.65
    apped
    -0.63
    POSITIVE LOGITS
    terday
    0.93
     shif
    0.69
    about
    0.66
     upside
    0.66
    agra
    0.65
    CVE
    0.65
    laus
    0.64
    FontSize
    0.64
    hift
    0.64
     assum
    0.62
    Act Density 0.018%

    No Known Activations