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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and government actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    opter
    -1.11
    wered
    -1.02
    lihood
    -0.92
    dates
    -0.90
    Gy
    -0.90
    Else
    -0.88
    obyl
    -0.87
    chel
    -0.87
     sailors
    -0.87
    ixture
    -0.86
    POSITIVE LOGITS
    enstein
    1.18
     Governor
    1.05
     Cuomo
    1.03
     governor
    1.02
    esses
    0.99
     vetoed
    0.96
    robe
    0.92
    PDATE
    0.92
    govern
    0.91
    Govern
    0.91
    Act Density 1.282%

    No Known Activations