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

    Neuronpedia

    INDEX
    Explanations

    phrases related to how individuals are treated by others

    oai_token-act-pair · gpt-3.5-turbo

    instances of people being treated in various ways, particularly in terms of respect and dignity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     circulation
    -0.65
     linking
    -0.64
     prediction
    -0.62
     Swing
    -0.60
    yrus
    -0.58
     Recall
    -0.56
    kb
    -0.56
     predictor
    -0.55
    utherford
    -0.55
    marks
    -0.55
    POSITIVE LOGITS
     differently
    1.15
     harshly
    1.02
     unfairly
    0.99
     respectfully
    0.99
     kindly
    0.96
     unequ
    0.94
     humane
    0.91
     hosp
    0.86
     accordingly
    0.85
     favorably
    0.83
    Act Density 0.185%

    No Known Activations