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

    Neuronpedia

    INDEX
    Explanations

    words that start with "Po" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Po"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.70
     EDITION
    -0.70
    ATIONAL
    -0.67
     Commodore
    -0.66
    ividual
    -0.64
     Monarch
    -0.63
     Nept
    -0.63
     Transparency
    -0.61
    UAL
    -0.61
     à¨
    -0.61
    POSITIVE LOGITS
    pper
    1.16
    ppy
    1.09
    inters
    1.07
    icket
    1.04
    ops
    1.02
    pping
    1.02
    etry
    1.00
    ppel
    0.99
    Po
    0.99
    zie
    0.98
    Act Density 0.013%

    No Known Activations