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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal and governmental constructs, specifically in the context of politics and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouf
    -0.83
    thora
    -0.82
    terday
    -0.80
    ĸļ
    -0.71
    ensibly
    -0.70
    iasis
    -0.70
    niper
    -0.69
     Originally
    -0.68
     Hebdo
    -0.68
    hua
    -0.65
    POSITIVE LOGITS
     entities
    1.03
     endeavors
    1.01
     factors
    0.98
     counterparts
    0.98
     pursuits
    0.98
     jurisdictions
    0.97
     sources
    0.95
     contenders
    0.94
     forms
    0.92
     distractions
    0.92
    Act Density 0.156%

    No Known Activations