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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the decisions and actions of various groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to decisions and actions made by various leaders or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctica
    -0.71
    ibble
    -0.71
     resil
    -0.64
    mol
    -0.63
    perture
    -0.63
    é¾įåĸļ士
    -0.62
    strip
    -0.62
    fml
    -0.62
    aan
    -0.61
    NetMessage
    -0.60
    POSITIVE LOGITS
     passers
    0.87
     politicians
    0.77
     governors
    0.75
     supervisors
    0.73
     pundits
    0.72
     bureaucrats
    0.72
     individuals
    0.72
     believers
    0.72
     electors
    0.71
     those
    0.70
    Act Density 0.151%

    No Known Activations