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

    Neuronpedia

    INDEX
    Explanations

    technical discussions or opinions related to computer processors

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.97
     adversaries
    -0.87
     eleph
    -0.75
     psychiat
    -0.73
     operating
    -0.73
    utical
    -0.72
     undermin
    -0.71
     foes
    -0.70
     hemor
    -0.70
     Mub
    -0.69
    POSITIVE LOGITS
    Reply
    1.30
    reply
    1.11
    Member
    1.01
    nice
    0.97
    Thread
    0.93
    Posted
    0.92
    lol
    0.90
    Posts
    0.88
    Hi
    0.87
    Repl
    0.86
    Act Density 10.512%

    No Known Activations