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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political power and influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases reflecting political challenges and pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Variant
    -0.70
     NAD
    -0.68
     Sensor
    -0.66
     Bits
    -0.65
     Regist
    -0.63
     mats
    -0.63
     Pwr
    -0.61
     Mages
    -0.59
    Origin
    -0.59
     CLS
    -0.57
    POSITIVE LOGITS
     presidency
    1.18
     Cabinet
    0.97
     reelection
    0.96
     aides
    0.96
     himself
    0.95
     appointing
    0.94
     appoint
    0.94
     impeachment
    0.94
     veto
    0.93
     subordinates
    0.91
    Act Density 1.142%

    No Known Activations