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

    Neuronpedia

    INDEX
    Explanations

    references to international organizations or agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of opposition or dissent against political figures or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    affected
    -0.70
    lehem
    -0.70
    umin
    -0.62
     istg
    -0.61
    rieved
    -0.61
    jured
    -0.61
    mble
    -0.61
    aceae
    -0.61
    ordial
    -0.60
     Affect
    -0.60
    POSITIVE LOGITS
     policies
    1.17
     proposals
    1.10
     imposition
    1.06
     proposal
    1.03
     proposed
    0.96
     legalization
    0.95
     practices
    0.93
     stance
    0.93
     labeling
    0.93
     dogma
    0.93
    Act Density 0.520%

    No Known Activations