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

    Neuronpedia

    INDEX
    Explanations

    security-related terms and topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arro
    -0.80
    qt
    -0.75
    nik
    -0.74
    sbm
    -0.72
    quit
    -0.71
     Tales
    -0.71
     Soup
    -0.70
     Flames
    -0.69
    quet
    -0.69
     Clown
    -0.68
    POSITIVE LOGITS
     dignity
    1.16
     wellbeing
    1.14
    Privacy
    1.10
     integrity
    1.08
     sustainability
    1.07
     privacy
    1.07
     sanitation
    1.05
     hygiene
    1.03
     accountability
    1.03
     liberties
    1.02
    Act Density 0.194%

    No Known Activations