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

    Neuronpedia

    INDEX
    Explanations

    mentions of social issues and societal observations related to various aspects of life

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    -0.46
     MLB
    -0.46
     Major
    -0.45
    ortium
    -0.44
     SAP
    -0.44
    ADVERTISEMENT
    -0.42
     NOAA
    -0.42
     Indian
    -0.41
     Gand
    -0.41
     Polit
    -0.41
    POSITIVE LOGITS
     alike
    0.49
    Reviewed
    0.46
    xual
    0.46
    queue
    0.44
    ttes
    0.44
    sense
    0.43
     pudding
    0.43
     hierarch
    0.43
    eers
    0.43
     rul
    0.43
    Act Density 7.192%

    No Known Activations