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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violations or infractions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal violations or breaches of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acs
    -0.76
    onna
    -0.73
    uilding
    -0.69
    esses
    -0.67
    hin
    -0.66
    ppa
    -0.66
     merry
    -0.66
    reau
    -0.65
    gre
    -0.64
    igrants
    -0.63
    POSITIVE LOGITS
     norms
    1.11
     protocol
    0.85
     norm
    0.85
     rights
    0.84
     confidentiality
    0.84
     jurisdiction
    0.82
    Ö¼
    0.82
     principles
    0.81
     principle
    0.80
    ĨĴ
    0.80
    Act Density 0.194%

    No Known Activations