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

    Neuronpedia

    INDEX
    Explanations

    political figures and government-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     futures
    -0.76
     IMAGES
    -0.73
     selves
    -0.72
    rift
    -0.72
    rossover
    -0.70
     traject
    -0.69
    acters
    -0.66
     hybrids
    -0.66
    tainment
    -0.65
    itars
    -0.64
    POSITIVE LOGITS
     veto
    1.34
     appoint
    1.28
     vetoed
    1.27
     presided
    1.16
     appointed
    1.11
     decree
    1.05
     appointing
    1.02
     administration
    1.01
     office
    1.01
     overseeing
    1.00
    Act Density 0.686%

    No Known Activations