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

    Neuronpedia

    INDEX
    Explanations

    themes related to control, conformity, and individuality in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ureka
    -0.14
    ascus
    -0.14
    ê
    -0.14
    Ãłi
    -0.13
    695
    -0.13
     ayır
    -0.13
    utex
    -0.12
    atsby
    -0.12
     tiế
    -0.12
    ibold
    -0.12
    POSITIVE LOGITS
     obedience
    0.50
     obedient
    0.49
     obed
    0.48
     submission
    0.47
     submissive
    0.44
     obey
    0.44
     obe
    0.40
     compliance
    0.40
     Submission
    0.39
     serv
    0.38
    Act Density 0.501%

    No Known Activations