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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts related to societal issues and moral dilemmas

    oai_token-act-pair · gpt-3.5-turbo

    concepts associated with societal issues and systemic inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Updated
    -0.72
     Leone
    -0.71
    ipop
    -0.70
    ovember
    -0.69
     congratulations
    -0.67
     Bleach
    -0.65
     Supplement
    -0.63
     expired
    -0.61
     PHOTO
    -0.60
     Klux
    -0.58
    POSITIVE LOGITS
     fallacy
    1.12
    lessness
    1.09
    ogeneity
    1.06
    isms
    1.03
     hypothesis
    1.03
     paradigm
    1.02
     principle
    1.00
     inherent
    0.99
    uality
    0.99
    ologies
    0.98
    Act Density 0.443%

    No Known Activations