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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government, authority, and accountability

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government and its influence or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moe
    -0.83
     resembled
    -0.76
    \-
    -0.74
    ecided
    -0.73
    isexual
    -0.70
     besides
    -0.69
    haus
    -0.69
     Skip
    -0.68
    aday
    -0.68
     Anyway
    -0.67
    POSITIVE LOGITS
     dictates
    1.26
    ocratic
    1.14
     Constitution
    1.11
     ideals
    1.10
     slightest
    1.09
    ocracy
    1.09
     totality
    1.08
     greatest
    1.06
    ocrats
    1.06
     tyranny
    1.03
    Act Density 0.354%

    No Known Activations