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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral dilemmas and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quotient
    -0.17
    storybook
    -0.15
    yssey
    -0.15
    ubic
    -0.15
    rette
    -0.15
    linger
    -0.14
    pedo
    -0.14
     ÑħозÑı
    -0.14
    RenderTarget
    -0.14
    fade
    -0.14
    POSITIVE LOGITS
     utility
    0.21
     Utility
    0.18
     rewards
    0.17
     welfare
    0.17
     pleasure
    0.16
     ple
    0.16
    utility
    0.15
     subjects
    0.15
     utilities
    0.15
     Faction
    0.15
    Act Density 0.009%

    No Known Activations