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

    Neuronpedia

    INDEX
    Explanations

    mentions of government actions and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONT
    -0.78
    sbm
    -0.78
     Tome
    -0.76
     Plate
    -0.72
    tom
    -0.69
     Daylight
    -0.68
     Width
    -0.68
    vill
    -0.66
    Ô
    -0.65
    ussen
    -0.65
    POSITIVE LOGITS
     Accountability
    1.05
     shutdown
    0.99
     bureaucracy
    0.95
     agencies
    0.95
     watchdog
    0.91
     contractor
    0.90
     agency
    0.89
     coffers
    0.84
     funded
    0.84
    arily
    0.82
    Act Density 0.054%

    No Known Activations