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

    Neuronpedia

    INDEX
    Explanations

    email-related text, including subscription prompts and requests for verification

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mson
    -0.72
     Curve
    -0.70
    wagon
    -0.69
    anu
    -0.69
    andom
    -0.66
    Registered
    -0.64
    omon
    -0.64
    pex
    -0.64
    oret
    -0.64
    _>
    -0.60
    POSITIVE LOGITS
     journalism
    0.69
     embed
    0.65
     transcription
    0.62
     promotions
    0.58
     promotional
    0.58
     giveaways
    0.57
     Privacy
    0.56
     redistribution
    0.55
     domains
    0.55
     graphics
    0.55
    Act Density 13.204%

    No Known Activations