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

    Neuronpedia

    INDEX
    Explanations

    references to articles in prominent publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of well-known publications or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strap
    -0.74
    obyl
    -0.69
     checkpoints
    -0.68
    ulkan
    -0.68
    wards
    -0.68
     tours
    -0.67
    ase
    -0.65
    ucha
    -0.64
     inspecting
    -0.64
     deployments
    -0.64
    POSITIVE LOGITS
     journal
    1.24
     Huffington
    1.23
     Observer
    1.20
     Journal
    1.20
     Guardian
    1.17
     Daily
    1.15
     Telegraph
    1.08
     Weekly
    1.07
     Lancet
    1.06
     Gazette
    1.06
    Act Density 0.109%

    No Known Activations