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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human rights

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     circulation
    -0.76
     popcorn
    -0.66
     railways
    -0.64
     plates
    -0.63
     potato
    -0.63
    thumbnails
    -0.62
     learning
    -0.62
     railroad
    -0.62
     shrink
    -0.61
     mercury
    -0.60
    POSITIVE LOGITS
     Accountability
    1.03
     Rights
    0.96
     Fighters
    0.93
     Lobby
    0.90
     Tribunal
    0.87
     Aid
    0.86
     Assistance
    0.85
     Commission
    0.82
     Situation
    0.81
     Content
    0.80
    Act Density 0.031%

    No Known Activations