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

    Neuronpedia

    INDEX
    Explanations

    references to human rights and related legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human rights and their protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apeake
    -0.76
    icol
    -0.73
    angelo
    -0.72
    rosso
    -0.72
    Rot
    -0.72
    prep
    -0.71
    balls
    -0.70
    mallow
    -0.70
    scan
    -0.69
    gall
    -0.69
    POSITIVE LOGITS
     freedoms
    0.84
     emancipation
    0.79
     equality
    0.73
     citizenship
    0.72
    ļéĨĴ
    0.70
     protections
    0.69
     privacy
    0.67
    ascript
    0.66
     justices
    0.66
     entitle
    0.66
    Act Density 0.429%

    No Known Activations