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

    Neuronpedia

    INDEX
    Explanations

    references to political entities or systems, specifically republics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "republic" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Oracle
    -0.83
    Bird
    -0.72
    Visual
    -0.70
    Cube
    -0.70
     Precision
    -0.70
    Companies
    -0.69
     Angels
    -0.69
     Rockets
    -0.67
    Adv
    -0.67
    Effects
    -0.66
    POSITIVE LOGITS
     republic
    1.23
     Seym
    1.12
    rats
    0.99
     revol
    0.85
     elector
    0.84
     unification
    0.82
    ocrat
    0.81
     citiz
    0.81
     socialism
    0.77
    wide
    0.77
    Act Density 0.012%

    No Known Activations