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

    Neuronpedia

    INDEX
    Explanations

    technical information related to computer hardware components and administration instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     charm
    -0.68
     footing
    -0.67
     whine
    -0.66
     smack
    -0.66
     aging
    -0.65
     laughter
    -0.64
    rad
    -0.64
     hust
    -0.63
     imperson
    -0.63
     ageing
    -0.62
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.20
    ³³³
    1.17
    ³³³³
    1.08
    ³³³³³³³³
    1.01
    RESULTS
    1.00
    Example
    0.97
    Additionally
    0.95
    Conclusion
    0.94
    Posted
    0.94
    Learn
    0.93
    Act Density 1.071%

    No Known Activations