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

    Neuronpedia

    INDEX
    Explanations

    computational terms and concepts within discussions on technologies, laws, and regulations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    sb
    -0.65
    ymm
    -0.64
     bra
    -0.62
     Yelp
    -0.61
    perse
    -0.61
    lette
    -0.59
     sqor
    -0.59
     Zip
    -0.58
     bragging
    -0.57
    zan
    -0.57
    POSITIVE LOGITS
     thereof
    1.00
     process
    0.85
     of
    0.84
     OF
    0.71
    ieth
    0.70
    ghai
    0.69
    athering
    0.69
    UTH
    0.68
    itial
    0.67
    of
    0.67
    Act Density 9.952%

    No Known Activations