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

    Neuronpedia

    INDEX
    Explanations

    interview-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to videos or interviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cig
    -0.70
     cakes
    -0.67
     Projects
    -0.67
     journals
    -0.65
     literature
    -0.65
    ictions
    -0.65
     disciplines
    -0.65
     systematic
    -0.65
     schemes
    -0.64
     novels
    -0.64
    POSITIVE LOGITS
    embed
    1.08
     embedded
    1.06
     below
    1.01
     clip
    0.99
    video
    0.94
    below
    0.91
     transcript
    0.88
     embed
    0.88
    above
    0.87
    VID
    0.87
    Act Density 0.178%

    No Known Activations