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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral values and personal development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ond
    -0.16
     preg
    -0.15
    alez
    -0.15
     newcomer
    -0.14
    Chain
    -0.14
     gangs
    -0.14
    nga
    -0.14
    riz
    -0.13
     knack
    -0.13
    bies
    -0.13
    POSITIVE LOGITS
     human
    0.32
     citizen
    0.31
     citizens
    0.31
    cit
    0.29
    Cit
    0.28
     Citizens
    0.27
     Citizen
    0.27
     humans
    0.27
     citiz
    0.26
    human
    0.26
    Act Density 0.159%

    No Known Activations