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

    Neuronpedia

    INDEX
    Explanations

    ads or promotional content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    assic
    -0.65
     mates
    -0.61
    gran
    -0.61
    amen
    -0.61
     masse
    -0.61
     Dull
    -0.60
    mate
    -0.58
    teenth
    -0.58
    kaya
    -0.58
     marsh
    -0.55
    POSITIVE LOGITS
    <|endoftext|>
    0.84
    Comments
    0.83
     Subscribe
    0.78
    edin
    0.76
     Thumbnails
    0.76
     Helpful
    0.74
     Stories
    0.73
     Comments
    0.73
    qus
    0.73
    able
    0.72
    Act Density 0.024%

    No Known Activations