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

    Neuronpedia

    INDEX
    Explanations

    comments and reviews, potentially related to online forums or feedback websites

    oai_token-act-pair · gpt-3.5-turbo

    formatting related to user-generated content and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.82
    issued
    -0.69
    worthiness
    -0.66
    anticipated
    -0.64
     separately
    -0.64
    entimes
    -0.64
    setting
    -0.64
     controls
    -0.63
    MORE
    -0.63
     textbooks
    -0.63
    POSITIVE LOGITS
     Anonymous
    1.23
     john
    1.20
     david
    1.19
    Anonymous
    1.07
     dan
    1.06
     dj
    1.06
     kb
    1.05
     jo
    1.03
    jon
    1.02
    mr
    1.02
    Act Density 0.197%

    No Known Activations