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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of dignity

    oai_token-act-pair · gpt-3.5-turbo

    references to dignity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ack
    -0.75
    suggest
    -0.66
    WER
    -0.66
     fielded
    -0.66
     Vaj
    -0.64
    vik
    -0.64
    addon
    -0.64
    enegger
    -0.60
    fleet
    -0.60
    HEAD
    -0.60
    POSITIVE LOGITS
     dignity
    1.16
    ility
    0.88
    ilege
    0.86
    ously
    0.81
    ably
    0.78
    acies
    0.77
     Dialogue
    0.77
    eous
    0.76
     Haram
    0.76
     equality
    0.75
    Act Density 0.008%

    No Known Activations