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

    Neuronpedia

    INDEX
    Explanations

    mentions of human rights issues

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights-related concepts and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barcl
    -0.62
     FI
    -0.62
     Buckingham
    -0.60
    creen
    -0.60
    EMP
    -0.60
     MPH
    -0.60
     compliment
    -0.59
     fuse
    -0.59
     Mechdragon
    -0.59
    RET
    -0.59
    POSITIVE LOGITS
    itarian
    1.47
     Rights
    1.30
     rights
    1.27
    rights
    1.19
    itar
    1.16
     trafficking
    1.08
     beings
    1.06
     Traff
    1.00
    zee
    0.95
     traffickers
    0.93
    Act Density 0.024%

    No Known Activations