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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political governments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government entities or references to government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONT
    -0.71
     Loop
    -0.71
    Ô
    -0.68
    Rank
    -0.68
    meyer
    -0.66
     Mortal
    -0.65
    bleacher
    -0.64
     Fortune
    -0.64
    colo
    -0.63
     Plate
    -0.62
    POSITIVE LOGITS
     ministers
    1.01
    arians
    0.92
     minister
    0.84
     planners
    0.84
     shutdown
    0.84
     departments
    0.83
     Ministers
    0.83
     appoint
    0.83
     coffers
    0.80
     helicop
    0.79
    Act Density 0.054%

    No Known Activations