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

    Neuronpedia

    INDEX
    Explanations

    contractions involving some form of possessive pronoun or proper noun

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.86
    Generic
    -0.78
    Built
    -0.72
    Specific
    -0.69
    Improved
    -0.68
    )=(
    -0.67
    Advanced
    -0.67
    STRUCT
    -0.66
    Filename
    -0.66
    Located
    -0.64
    POSITIVE LOGITS
     Jenna
    1.26
     Katie
    1.24
     Juliet
    1.21
     Maggie
    1.21
     Erin
    1.21
     Kristen
    1.19
     Julie
    1.19
     Sarah
    1.19
     Jessica
    1.18
     Stephanie
    1.18
    Act Density 0.102%

    No Known Activations