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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    themes related to political self-interest and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assium
    -0.58
    interrupted
    -0.58
    ortium
    -0.57
     mosqu
    -0.56
    staking
    -0.56
    inguished
    -0.55
    marked
    -0.55
    availability
    -0.54
    etheless
    -0.54
    requisite
    -0.53
    POSITIVE LOGITS
     truths
    0.81
     blindly
    0.74
     immoral
    0.73
     stupid
    0.72
     scapego
    0.72
     paycheck
    0.70
     oneself
    0.70
     ignorant
    0.69
     morals
    0.68
     righteousness
    0.68
    Act Density 1.252%

    No Known Activations