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

    Neuronpedia

    INDEX
    Explanations

    terms related to political matters or situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    tered
    -0.84
    ibles
    -0.80
    olen
    -0.78
    wered
    -0.75
    lished
    -0.75
    imates
    -0.74
    imus
    -0.72
    upon
    -0.71
     Colt
    -0.70
    plin
    -0.69
    POSITIVE LOGITS
     correctness
    1.41
     upheaval
    1.07
     instability
    0.99
     turmoil
    0.98
     uphe
    0.94
     leaders
    0.92
     clout
    0.91
     stability
    0.89
     prisoners
    0.89
     parties
    0.89
    Act Density 0.036%

    No Known Activations