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

    Neuronpedia

    INDEX
    Explanations

    references to political issues and officials

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disagre
    -2.30
     increa
    -2.30
     affor
    -2.29
     impra
    -2.29
     inev
    -2.23
     fta
    -2.21
     encomp
    -2.20
     reluct
    -2.17
     maneu
    -2.17
     squa
    -2.16
    POSITIVE LOGITS
     We
    1.07
     It
    1.06
    ").
    1.04
     They
    1.03
     There
    1.00
    ”.
    0.99
    ".
    0.99
     You
    0.99
     That
    0.98
     But
    0.98
    Act Density 0.217%

    No Known Activations