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

    Neuronpedia

    INDEX
    Explanations

    phrases related to faithfulness and obedience

    oai_token-act-pair · gpt-3.5-turbo

    terms related to faithfulness and loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.74
    eways
    -0.73
    NetMessage
    -0.72
     Mehran
    -0.70
    ipl
    -0.67
    ofi
    -0.66
    rill
    -0.64
    azine
    -0.63
    nesota
    -0.63
    USH
    -0.61
    POSITIVE LOGITS
    vironment
    0.84
     servant
    0.83
     faithful
    0.80
     obe
    0.79
    aith
    0.77
     adherence
    0.74
     obedience
    0.73
    isance
    0.71
    ciples
    0.71
    lihood
    0.71
    Act Density 0.055%

    No Known Activations