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

    Neuronpedia

    INDEX
    Explanations

    references to experiences and comparisons in a specific context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.72
    TypedValue
    -0.58
     restera
    -0.50
    To
    -0.49
     appartient
    -0.49
    PrintStream
    -0.48
    to
    -0.47
    Search
    -0.47
     devra
    -0.47
    andolo
    -0.47
    POSITIVE LOGITS
     hairc
    1.21
     thut
    1.10
     scrat
    1.09
     swarovski
    1.06
     hentai
    1.06
     milf
    1.05
     tew
    1.01
     fta
    1.00
     ?...
    0.99
     greate
    0.99
    Act Density 0.436%

    No Known Activations