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

    Neuronpedia

    INDEX
    Explanations

    words related to geopolitical events and government actions, particularly within the context of the United States

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    onna
    -0.70
    agascar
    -0.67
    vu
    -0.66
    daq
    -0.65
     viol
    -0.65
     ahead
    -0.61
    etti
    -0.61
     torches
    -0.59
    rex
    -0.58
    udder
    -0.58
    POSITIVE LOGITS
     confines
    1.66
     bounds
    1.52
     boundaries
    1.22
     limits
    1.21
     borders
    1.11
     scope
    1.06
     parameters
    1.04
     radius
    1.00
     perimeter
    0.96
     realm
    0.93
    Act Density 13.608%

    No Known Activations