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

    Neuronpedia

    INDEX
    Explanations

    phrases related to honor and respect

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with honor and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acid
    -0.77
    akeru
    -0.76
     tents
    -0.72
    ullivan
    -0.72
     exacerb
    -0.72
    soDeliveryDate
    -0.71
     gears
    -0.70
     buses
    -0.70
    */(
    -0.69
     mosquit
    -0.69
    POSITIVE LOGITS
     dignity
    0.95
     honorable
    0.88
    Merit
    0.81
     duly
    0.77
     dign
    0.76
    rity
    0.72
     exemplary
    0.72
     decency
    0.71
     bravery
    0.71
     chast
    0.71
    Act Density 0.309%

    No Known Activations