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

    Neuronpedia

    INDEX
    Explanations

    references to issues related to privacy and civil liberties

    oai_token-act-pair · gpt-3.5-turbo

    topics related to privacy rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.82
    annis
    -0.82
    ×Ļ×
    -0.75
    Production
    -0.73
    cki
    -0.68
    oric
    -0.66
    unes
    -0.65
    hani
    -0.65
    amen
    -0.65
    hyde
    -0.64
    POSITIVE LOGITS
     privacy
    1.02
     protections
    0.90
     rights
    0.84
     safeguards
    0.84
     anonymity
    0.82
     suits
    0.80
     Rights
    0.76
     Liberties
    0.73
    rights
    0.73
     protection
    0.73
    Act Density 0.015%

    No Known Activations