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

    Neuronpedia

    INDEX
    Explanations

    phrases involving personal decision-making and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /commons
    -0.16
    ailer
    -0.15
    asury
    -0.15
    iteur
    -0.15
    isky
    -0.15
    isco
    -0.15
    ÑģпÑĸлÑĮ
    -0.15
    raya
    -0.15
    tement
    -0.15
    ioxid
    -0.14
    POSITIVE LOGITS
    å¸Ń
    0.17
     Schultz
    0.15
     RW
    0.15
    Ñįн
    0.14
    urable
    0.13
    nis
    0.13
    uj
    0.13
     Young
    0.13
     People
    0.13
    они
    0.13
    Act Density 0.300%

    No Known Activations