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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Meg" with variations in capitalization

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or entity named "Meg."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.82
     Grounds
    -0.74
     Sense
    -0.71
    enegger
    -0.66
     Paradox
    -0.65
    velt
    -0.65
    bable
    -0.64
    xual
    -0.64
    unct
    -0.64
    odge
    -0.63
    POSITIVE LOGITS
    abytes
    1.31
    abyte
    1.27
    awatts
    1.09
    apixel
    1.05
    acity
    0.96
    apolis
    0.96
    atron
    0.95
    aton
    0.94
    atis
    0.94
    abases
    0.91
    Act Density 0.015%

    No Known Activations