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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical infrastructure projects and updates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     THESE
    -0.30
     Ivanka
    -0.28
     Barack
    -0.28
    Downloadha
    -0.28
    20439
    -0.28
    BuyableInstoreAndOnline
    -0.27
     namely
    -0.26
     Izan
    -0.25
     Irma
    -0.25
     Considering
    -0.25
    POSITIVE LOGITS
    oret
    0.28
    eway
    0.28
    oka
    0.27
    eways
    0.26
    ast
    0.26
    est
    0.26
    ior
    0.26
    iler
    0.26
    gh
    0.25
    itol
    0.25
    Act Density 3.718%

    No Known Activations