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

    Neuronpedia

    INDEX
    Explanations

    references to dignity or dignified behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to dignity and respectful treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kindle
    -0.74
     Wonderland
    -0.70
     Archangel
    -0.68
     Reloaded
    -0.66
     thinly
    -0.66
    è¦ļéĨĴ
    -0.65
     Heard
    -0.65
     Angry
    -0.63
     Spear
    -0.63
     Sapp
    -0.62
    POSITIVE LOGITS
     dign
    1.46
    itary
    1.32
    ified
    1.18
    itas
    1.05
     Dign
    0.93
    uci
    0.92
    uitous
    0.90
     citiz
    0.87
    idad
    0.87
     honoured
    0.86
    Act Density 0.002%

    No Known Activations