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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political entities and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to political groups and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.75
     beforehand
    -0.73
    duction
    -0.71
     followed
    -0.71
     according
    -0.70
     unless
    -0.70
     ahead
    -0.69
    estyles
    -0.68
    smanship
    -0.68
    rection
    -0.66
    POSITIVE LOGITS
     neocons
    1.11
     neoliberal
    1.09
     Tea
    1.08
     Clintons
    1.06
    ocrats
    1.06
     bourgeoisie
    1.04
     populist
    1.03
     reactionary
    1.02
     Occupy
    1.01
    ocratic
    0.98
    Act Density 0.291%

    No Known Activations