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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal structures, economic systems, and political discourse

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.52
    REM
    -0.49
    cture
    -0.49
    vae
    -0.47
    ibrary
    -0.46
     Flake
    -0.44
    ï¸
    -0.44
    izon
    -0.44
    Greek
    -0.43
    aretz
    -0.43
    POSITIVE LOGITS
     thereof
    0.92
     alike
    0.78
     accompanying
    0.70
     therein
    0.69
     thereto
    0.67
     accordingly
    0.66
     respectively
    0.64
     attendant
    0.59
     consequ
    0.58
     resultant
    0.58
    Act Density 14.168%

    No Known Activations