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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal documents or regulations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     nodd
    -0.70
     boun
    -0.69
     strangers
    -0.69
     unlucky
    -0.68
     stranger
    -0.67
     stray
    -0.67
     predec
    -0.67
     stubborn
    -0.67
     manif
    -0.66
     passers
    -0.66
    POSITIVE LOGITS
     Includes
    1.20
     These
    1.18
     Additionally
    1.17
     Retrieved
    1.16
     Also
    1.07
     Specifically
    1.07
     NOTE
    1.06
     Such
    1.06
     Originally
    1.05
     Among
    1.02
    Act Density 0.364%

    No Known Activations