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

    Neuronpedia

    INDEX
    Explanations

    references to social justice and ethical issues, particularly related to rights, exploitation, honesty, and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    discussions around societal issues and human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.72
    çĶ°
    -0.67
    '.
    -0.63
    ''.
    -0.63
    }.
    -0.61
    nown
    -0.61
    `.
    -0.60
    Recommend
    -0.59
     âĵĺ
    -0.59
     unfocusedRange
    -0.58
    POSITIVE LOGITS
     democracies
    0.76
     intellectually
    0.69
     passively
    0.68
    itar
    0.66
     rational
    0.66
     truths
    0.66
     oneself
    0.65
     finite
    0.65
     presupp
    0.64
     democratically
    0.63
    Act Density 1.511%

    No Known Activations