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

    Neuronpedia

    INDEX
    Explanations

    individuals in positions of authority or discussing government-related matters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yrs
    -1.04
    orem
    -0.94
    etts
    -0.94
    ograph
    -0.92
    stakes
    -0.91
    ĸļ
    -0.91
    olen
    -0.87
     Gutenberg
    -0.86
    oven
    -0.85
    ographed
    -0.84
    POSITIVE LOGITS
    uty
    0.99
     deputy
    0.83
     sher
    0.81
     sheriff
    0.81
     clerks
    0.80
    geon
    0.73
     confinement
    0.73
    chief
    0.72
    clips
    0.72
    riage
    0.72
    Act Density 2.191%

    No Known Activations