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

    Neuronpedia

    INDEX
    Explanations

    references to institutions related to research and policy, particularly think tanks

    oai_token-act-pair · gpt-3.5-turbo

    references to think tanks and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alogue
    -0.74
    amaz
    -0.74
    pain
    -0.70
     satisf
    -0.66
    Complete
    -0.65
    illard
    -0.65
    uder
    -0.65
     Butcher
    -0.64
     handc
    -0.64
     goose
    -0.64
    POSITIVE LOGITS
    arians
    0.99
    arian
    0.84
     instit
    0.82
     Institution
    0.82
     chaired
    0.80
     institute
    0.80
     convened
    0.78
    uments
    0.77
     adviser
    0.75
     economists
    0.75
    Act Density 0.101%

    No Known Activations