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

    Neuronpedia

    INDEX
    Explanations

    phrases related to how individuals are treated or perceived by others

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference treating individuals with dignity and respect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.79
    è¦ļéĨĴ
    -0.68
     Rivals
    -0.67
     obser
    -0.67
    atoon
    -0.66
     confir
    -0.66
    ģĸ
    -0.65
    yrus
    -0.64
    anyon
    -0.62
     raft
    -0.61
    POSITIVE LOGITS
     respectfully
    0.79
     differently
    0.78
     kindly
    0.78
     Orient
    0.76
     seriously
    0.74
     pear
    0.71
    Subject
    0.69
     humane
    0.67
     crap
    0.65
     objectively
    0.64
    Act Density 0.112%

    No Known Activations