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

    Neuronpedia

    INDEX
    Explanations

    words related to legality and constitutional issues

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of unconstitutionality and violations of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oa
    -0.66
     manager
    -0.65
     experience
    -0.65
     Mash
    -0.64
     management
    -0.63
     Dri
    -0.63
     trainer
    -0.62
     Lab
    -0.62
     dwell
    -0.61
    es
    -0.61
    POSITIVE LOGITS
     unconstitutional
    3.61
     constitutionally
    1.56
     discriminatory
    1.53
    constitutional
    1.48
     unlawful
    1.48
     immoral
    1.32
     unjust
    1.28
     ineligible
    1.27
     unethical
    1.26
     objectionable
    1.25
    Act Density 0.015%

    No Known Activations